© 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
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 10954
    Prev
    Next
    INDEX
    Explanations

    phrases indicating the provision of information or insights in studies

    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
    msgSender
    -0.50
     Se
    -0.49
    Se
    -0.48
     linkovi
    -0.48
     expresa
    -0.47
    <eos>
    -0.45
    Reentrant
    -0.44
     initComponents
    -0.44
    サギ
    -0.44
     Walkover
    -0.43
    POSITIVE LOGITS
     Efq
    0.79
    EndContext
    0.73
     ModelExpression
    0.71
     Hift
    0.71
    ollectionView
    0.69
    OGND
    0.69
     himſelf
    0.67
     Monfieur
    0.66
     ſeveral
    0.62
     myſelf
    0.62
    Activations Density 0.084%

    No Known Activations