© 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. 4663
    Prev
    Next
    INDEX
    Explanations

    peacefully

    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
     referenties
    -0.76
     peacefully
    -0.74
    setVerticalGroup
    -0.73
    __':
    -0.71
     utafitiHapana
    -0.69
    ParallelGroup
    -0.67
     harmless
    -0.64
    featureID
    -0.64
    таратура
    -0.64
     виправивши
    -0.63
    POSITIVE LOGITS
    汰
    0.35
     Akhir
    0.35
     rotational
    0.34
    énieurs
    0.34
    rut
    0.34
    付け
    0.34
     of
    0.33
    ToSave
    0.33
    top
    0.33
    out
    0.32
    Activations Density 0.001%

    No Known Activations