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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 2-RES-MATRYOSHKA-DC
    4. 35
    Prev
    Next
    INDEX
    Explanations

    references to configuration parameters and hardware component identifiers

    oai_token-act-pair · gpt-4.1-nano
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     NSCoder
    -1.14
     المعيارى
    -1.05
    LookAnd
    -1.03
     ProtoMessage
    -1.02
     resourceCulture
    -1.01
    RenderAtEndOf
    -0.94
     ***!
    -0.93
    parsedMessage
    -0.92
    Lähteet
    -0.91
    })`
    -0.90
    POSITIVE LOGITS
    <
    2.95
     <
    2.45
    )<
    2.09
    .<
    2.03
    }<
    1.95
    :<
    1.92
    ;<
    1.87
    ,<
    1.83
     $<
    1.81
    ?<
    1.81
    Activations Density 2.310%

    No Known Activations