© 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. 5-CLT-HP
    7. 96200
    Prev
    Next
    INDEX
    Explanations

    in

    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
    PreferredItem
    -0.68
     surla
    -0.57
    interopRequire
    -0.55
     continúas
    -0.54
    RegressionTest
    -0.54
    oredCriteria
    -0.53
     isSet
    -0.52
    存于互联网档案馆
    -0.51
     AssemblyCulture
    -0.50
    MergeFrom
    -0.47
    POSITIVE LOGITS
     two
    0.75
    two
    0.66
     three
    0.63
     TWO
    0.63
    enumii
    0.62
    TWO
    0.59
     deux
    0.57
    zwei
    0.55
    three
    0.54
     THREE
    0.54
    Activations Density 0.001%

    No Known Activations