© 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. 20-CLT-HP
    7. 76555
    Prev
    Next
    INDEX
    Explanations

    bal

    np_max-act-logits · 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
    rungsseite
    -0.56
     Ammon
    -0.56
    envolvimento
    -0.49
    ЙТЕ
    -0.49
    υν
    -0.49
    iettivo
    -0.48
    مصادر
    -0.48
    ReusableCell
    -0.47
     oprot
    -0.47
    
    -0.46
    POSITIVE LOGITS
     mergeFrom
    0.64
    erdings
    0.55
     Audiodateien
    0.54
     betweenstory
    0.50
     jLabel
    0.50
    ---
    0.49
     =~
    0.47
    aray
    0.46
     Damas
    0.46
    marle
    0.46
    Activations Density 0.002%

    No Known Activations