© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 1-CLT-HP
    7. 15889
    Prev
    Next
    INDEX
    Explanations

    Research papers

    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
    yors
    -0.40
    ]>
    -0.39
     F
    -0.39
    >
    -0.38
     >
    -0.38
    ISupport
    -0.37
     who
    -0.36
    /
    -0.36
    <?,
    -0.36
    ()>
    -0.35
    POSITIVE LOGITS
     Moslem
    0.86
    CloseOperation
    0.85
     Мексичка
    0.83
     ModelExpression
    0.81
     الحره
    0.79
     صوتيه
    0.79
    ">//
    0.78
     Monfieur
    0.78
    WriteAttribute
    0.77
     $_"
    0.72
    Activations Density 0.034%

    No Known Activations