© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Initial Gemma-2B SAEs
    5. Gemma-2B
    7. Residual Stream
    9. 10-RES-JB
    11. 4086
    Prev
    Next
    INDEX
    Explanations

    the preposition "to" and its related usage in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    jbloom/Gemma-2b-Residual-Stream-SAEs/gemma_2b_blocks.10.hook_resid_post_16384
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    chanind/openwebtext-gemma
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    standard
    Context Size
    1,024
    Dataset
    ctigges/openwebtext-gemma-1024-cl
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    50
    +0.34
    1.6%
    1334
    +0.17
    0.8%
    1407
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1334
    +0.34
    0.05
    1141
    +0.17
    0.03
    1407
    +0.12
    0.03
    Negative Logits
    <bos>
    -2.05
    <?
    -0.76
     Cæsar
    -0.70
     forbear
    -0.68
    /**
    -0.67
     endow
    -0.66
     intersper
    -0.64
     seiz
    -0.63
    habited
    -0.63
    šech
    -0.62
    POSITIVE LOGITS
    Život
    0.75
     Dès
    0.68
    Pcd
    0.67
     Qualquer
    0.66
    iuo
    0.65
    ">...
    0.65
    Heya
    0.63
    Sooo
    0.62
     Muito
    0.62
    letterSpacing
    0.61
    Activations Density 0.102%

    No Known Activations