© 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. 20-CLT-HP
    7. 74689
    Prev
    Next
    INDEX
    Explanations

    period

    np_max-act-logits · 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
    AccessorTable
    -0.70
     ContentValues
    -0.69
    blockList
    -0.65
    üyada
    -0.61
    nettes
    -0.56
    󠁢
    -0.55
    RegressionTest
    -0.53
    agoza
    -0.51
    parsedMessage
    -0.51
    seteq
    -0.50
    POSITIVE LOGITS
    ac
    0.77
    co
    0.66
    ie
    0.52
     co
    0.51
     Ac
    0.49
    aarrggbb
    0.49
    TestingModule
    0.47
    acro
    0.47
    AC
    0.46
    aco
    0.46
    Activations Density 0.002%

    No Known Activations