© 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. Gemma-2-2B
    3. 12-RES-MATRYOSHKA-DC
    4. 21623
    Prev
    Next
    INDEX
    Explanations

    the closing parenthesis character

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.12.hook_resid_post
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    32,768
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    chanind/pile-uncopyrighted-gemma-1024-abbrv-1B
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Meksiku
    -0.69
    Demikian
    -0.57
     pngtree
    -0.57
    PositiveButton
    -0.56
     JpaRepository
    -0.53
     TokenType
    -0.53
    TypedDataSet
    -0.52
     nahilalakip
    -0.52
     iſt
    -0.52
     compréhen
    -0.50
    POSITIVE LOGITS
     Exacts
    0.61
    +#+#
    0.60
    ValueStyle
    0.59
     <=",
    0.59
     متعلقه
    0.54
     calendriers
    0.54
    <_>
    0.51
    رشف
    0.50
     ExecuteAsync
    0.49
     chance
    0.48
    Activations Density 0.000%

    No Known Activations