© 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. 11056
    Prev
    Next
    INDEX
    Explanations

    categories or classifications

    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
    AndEndTag
    -1.23
    parsedMessage
    -1.19
    contentLoaded
    -1.18
     cherchés
    -1.05
    PerformLayout
    -1.03
    IVEREF
    -1.03
    invokeLater
    -1.01
     ModelExpression
    -0.99
    SharedDtor
    -0.99
    InjectAttribute
    -0.97
    POSITIVE LOGITS
    wiki
    0.52
     edit
    0.45
    roups
    0.44
     peligros
    0.44
     sû
    0.44
     fossero
    0.43
     passaram
    0.42
     edição
    0.42
     sami
    0.42
     eccell
    0.42
    Activations Density 0.022%

    No Known Activations