© 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. 0-CLT-HP
    7. 94450
    Prev
    Next
    INDEX
    Explanations

    outpost

    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
     Stowe
    -1.01
     itſelf
    -0.80
     Reſ
    -0.77
    ophores
    -0.77
    SourceChecksum
    -0.77
     purpoſe
    -0.74
     pleaſure
    -0.74
    ſelves
    -0.73
     ſtate
    -0.73
     بيها
    -0.71
    POSITIVE LOGITS
     di
    0.65
     qu
    0.56
     del
    0.55
     to
    0.53
     fun
    0.49
    <?
    0.49
     true
    0.49
     dia
    0.49
     y
    0.48
     ver
    0.48
    Activations Density 1.595%

    No Known Activations