© 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. 4-CLT-HP
    7. 681
    Prev
    Next
    INDEX
    Explanations

    crowded or career/sports

    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
     gefüllt
    -0.63
     complètes
    -0.62
     démocr
    -0.60
     móvel
    -0.56
     judiciales
    -0.55
     juridiques
    -0.55
     Réponses
    -0.52
     variés
    -0.51
     recev
    -0.50
     vanligt
    -0.50
    POSITIVE LOGITS
    SPATH
    0.66
    发表于
    0.63
    ding
    0.59
     AssemblyCulture
    0.58
    libft
    0.56
     glyphicon
    0.54
    ktop
    0.54
    ">//
    0.53
    AccessorTable
    0.53
     others
    0.52
    Activations Density 0.004%

    No Known Activations