© 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. 95120
    Prev
    Next
    INDEX
    Explanations

    for

    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
     AssemblyCulture
    -0.89
    tvguidetime
    -0.71
    Geplaatst
    -0.64
    extAlignment
    -0.63
    SequentialGroup
    -0.59
    colgroup
    -0.59
    getDescriptor
    -0.56
    ()?;
    -0.56
    )");
    -0.54
     AssemblyTitle
    -0.54
    POSITIVE LOGITS
     those
    0.66
     you
    0.59
     the
    0.59
     anyone
    0.54
     we
    0.52
    Kết
    0.49
     dunque
    0.48
     be
    0.48
     fair
    0.47
     true
    0.47
    Activations Density 0.017%

    No Known Activations