© 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
    2. Gemma-2-2B
    3. 0-CLT-HP
    4. 94078
    Prev
    Next
    INDEX
    Explanations

    article/blog post

    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
    first
    -0.82
     first
    -0.68
    First
    -0.67
    abord
    -0.57
    最初の
    -0.55
    initial
    -0.55
     primeiro
    -0.55
     premières
    -0.53
    первых
    -0.53
    ↵
    -0.52
    POSITIVE LOGITS
    ]`
    0.81
     незавершена
    0.77
    esterday
    0.77
    berdayakan
    0.76
    */;
    0.75
    tvguidetime
    0.75
    displayquote
    0.75
    >");
    
    0.74
     désolés
    0.74
    олові
    0.74
    Activations Density 0.129%

    No Known Activations