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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Initial Gemma-2B-IT SAEs
    5. Gemma-2B-IT
    7. Residual Stream
    9. 12-RES-JB
    11. 11966
    Prev
    Next
    INDEX
    Explanations

    phrases containing prepositions followed by nouns or verbs

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    jbloom/Gemma-2b-IT-Residual-Stream-SAEs/gemma_2b_it_blocks.12.hook_resid_post_16384
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    HuggingFaceFW/fineweb
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    standard
    Context Size
    1,024
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    752
    +0.14
    0.4%
    1156
    +0.13
    0.4%
    198
    +0.10
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    752
    +0.14
    0.06
    1334
    +0.13
    0.06
    1156
    +0.10
    0.05
    Negative Logits
    !("{
    -0.69
    JHEP
    -0.65
    PerformLayout
    -0.61
     svolge
    -0.60
    ECONDS
    -0.59
    cheibe
    -0.57
    PageRoute
    -0.57
     CreateTagHelper
    -0.56
    Demografie
    -0.56
    Manbalar
    -0.55
    POSITIVE LOGITS
     fff
    0.68
    fordable
    0.68
     deleter
    0.67
     doman
    0.66
    ftra
    0.66
     yore
    0.64
     Mâ
    0.64
     Gén
    0.63
     spacy
    0.63
     fter
    0.63
    Activations Density 0.289%

    No Known Activations