© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-CLT-HP
    7. 307
    Prev
    Next
    INDEX
    Explanations

    technical descriptions

    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
     multi
    -1.05
     Multi
    -0.87
    multi
    -0.85
    Multi
    -0.83
     multiple
    -0.73
    MULT
    -0.73
     MULT
    -0.70
     MULTI
    -0.69
     multifunctional
    -0.67
     múltiple
    -0.66
    POSITIVE LOGITS
    >{@
    0.70
    thenReturn
    0.62
    inSlope
    0.61
    prache
    0.60
    coles
    0.60
     مشين
    0.60
     виправивши
    0.59
    تقاوى
    0.57
     referrerpolicy
    0.57
     /*#__
    0.56
    Activations Density 0.016%

    No Known Activations