© 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. 43637
    Prev
    Next
    INDEX
    Explanations

    Word fragments and URLs

    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
    MEN
    -0.69
    icana
    -0.68
    ica
    -0.63
     fumée
    -0.62
     fédé
    -0.59
     bienfaits
    -0.59
    ican
    -0.57
     enfans
    -0.57
     émissions
    -0.56
    mena
    -0.56
    POSITIVE LOGITS
    PerformLayout
    0.76
     Ouverture
    0.76
     Chwiliwch
    0.74
    abetes
    0.71
     nahilalakip
    0.69
    DebuggerStep
    0.67
    SourceChecksum
    0.64
    wahati
    0.63
     Rtl
    0.62
    SequentialGroup
    0.62
    Activations Density 0.053%

    No Known Activations