© 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. 0-CLT-HP
    7. 39935
    Prev
    Next
    INDEX
    Explanations

    variety of topics

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Wicidata
    -0.85
     مرئيه
    -0.74
    HostException
    -0.73
     يتيمه
    -0.71
    LEncoder
    -0.69
    ayage
    -0.69
    ituaries
    -0.67
    liath
    -0.66
     appelez
    -0.66
    hopped
    -0.65
    POSITIVE LOGITS
     disponibilités
    0.54
    tabular
    0.48
     different
    0.47
    tip
    0.47
    parsedMessage
    0.44
    сах
    0.44
    Whatever
    0.43
    ek
    0.43
     tip
    0.42
    itemize
    0.41
    Activations Density 0.148%

    No Known Activations