© 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. 1-CLT-HP
    7. 14471
    Prev
    Next
    INDEX
    Explanations

    band

    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
     band
    -2.05
     Band
    -1.82
    Band
    -1.80
    band
    -1.68
     bands
    -1.65
     BAND
    -1.60
    BAND
    -1.55
     Bands
    -1.53
    Bands
    -1.40
    bands
    -1.38
    POSITIVE LOGITS
    :✨
    0.84
     esternos
    0.68
    matchCondition
    0.63
    ništ
    0.59
     <<<<<<<<<<<<<<
    0.58
     VizieR
    0.57
    PerformLayout
    0.56
     estekak
    0.56
    CompleteListener
    0.56
    walks
    0.55
    Activations Density 0.009%

    No Known Activations