© 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. 191
    Prev
    Next
    INDEX
    Explanations

    URLs and web addresses

    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
    ValueStyle
    -0.77
     disambiguazione
    -0.74
     LUMP
    -0.74
     Anſ
    -0.73
    Tikang
    -0.72
    LookAnd
    -0.71
     Mahomet
    -0.71
     Chriftian
    -0.71
     fevere
    -0.70
     himſelf
    -0.70
    POSITIVE LOGITS
    ://
    2.67
    ://"
    1.39
    www
    1.27
     www
    1.09
    :\/\/
    0.88
    :///
    0.87
    ="//
    0.85
    Portale
    0.77
     http
    0.73
    ://$
    0.72
    Activations Density 0.447%

    No Known Activations