© 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. 1-CLT-HP
    7. 9447
    Prev
    Next
    INDEX
    Explanations

    names

    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
     robe
    -0.79
    robe
    -0.77
    хьтан
    -0.70
     فريبيس
    -0.69
     незавершена
    -0.64
    ReusableCell
    -0.63
     Robe
    -0.62
    hoeddwyd
    -0.61
     robes
    -0.60
    WebVitals
    -0.60
    POSITIVE LOGITS
     Lenti
    0.52
    bleau
    0.44
    łosi
    0.44
     bArr
    0.44
     gereken
    0.44
    武蔵
    0.43
     Savoy
    0.43
     Werk
    0.43
     Vor
    0.43
    前任
    0.42
    Activations Density 0.012%

    No Known Activations