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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Joseph Bloom · Initial Gemma-2B-IT SAEs
    3. Gemma-2B-IT
    4. Residual Stream
    5. 12-RES-JB
    6. 14425
    Prev
    Next
    INDEX
    Explanations

    verbs in some Slavic language

    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
    1778
    +0.19
    0.8%
    871
    +0.15
    0.6%
    538
    +0.13
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1778
    +0.19
    0.06
    1406
    +0.15
    0.05
    871
    +0.13
    0.04
    Negative Logits
     jeste
    -0.65
     šte
    -0.64
    Referencie
    -0.60
     pripra
    -0.58
     dovol
    -0.58
     tež
    -0.56
     približ
    -0.53
    andaag
    -0.52
     faceva
    -0.52
     moze
    -0.52
    POSITIVE LOGITS
     V
    1.06
    V
    1.05
     v
    0.99
    v
    0.92
     vanadium
    0.86
    Lma
    0.80
     vix
    0.79
     Vaugh
    0.78
    getV
    0.78
     vasto
    0.76
    Activations Density 0.223%

    No Known Activations