© 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. 5-CLT-HP
    7. 4446
    Prev
    Next
    INDEX
    Explanations

    inmates

    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
    ugan
    -0.46
    .
    -0.43
    Dap
    -0.41
     site
    -0.41
    inda
    -0.40
    ('
    -0.36
    k
    -0.36
     года
    -0.35
     .
    -0.35
    for
    -0.35
    POSITIVE LOGITS
    RectangleBorder
    0.95
     للمعارف
    0.87
     purpoſe
    0.86
     tartalomajánló
    0.85
     nahilalakip
    0.85
    tagHelperRunner
    0.84
     themſelves
    0.82
     myſelf
    0.82
     незавершена
    0.81
     greateſt
    0.79
    Activations Density 0.000%

    No Known Activations