© 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. 1-CLT-HP
    7. 12988
    Prev
    Next
    INDEX
    Explanations

    client, slave

    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
    ]")]
    -0.70
     MainAxisSize
    -0.68
     BoxFit
    -0.65
    ⓧ
    -0.64
    //
    -0.64
     createSlice
    -0.63
     мәкал
    -0.62
    ConstraintMaker
    -0.62
    cshtml
    -0.60
     виправивши
    -0.60
    POSITIVE LOGITS
    órum
    0.53
     NSMutable
    0.52
    RegressionTest
    0.51
     loops
    0.51
    الى
    0.49
    cze
    0.48
     looping
    0.48
    FBI
    0.47
    Demografia
    0.47
     LinkedHashMap
    0.46
    Activations Density 0.033%

    No Known Activations