Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 12-RES-MATRYOSHKA-DC
    4. 25521
    Prev
    Next
    INDEX
    Explanations

    numerical data and statistics in the context of research findings

    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
    DispatchToProps
    -0.66
    NOPQRST
    -0.44
     pre
    -0.43
     Treue
    -0.42
    PrototypeOf
    -0.41
     material
    -0.41
     non
    -0.40
    LayoutStyle
    -0.40
     Pre
    -0.40
     economy
    -0.40
    POSITIVE LOGITS
     jScrollPane
    0.81
    ();)
    0.78
     morire
    0.73
    tagHelperRunner
    0.73
     ProtoMessage
    0.71
    Personensuche
    0.70
     mourut
    0.70
     propOrder
    0.67
     bénévoles
    0.67
    tonode
    0.67
    Activations Density 0.011%

    No Known Activations