© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-CLT-HP
    7. 3195
    Prev
    Next
    INDEX
    Explanations

    additional information

    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
     are
    -0.53
    camente
    -0.52
     reassure
    -0.50
     assure
    -0.48
     Horowitz
    -0.48
    KEYCODE
    -0.45
     control
    -0.44
    ustra
    -0.43
    acas
    -0.43
     relate
    -0.42
    POSITIVE LOGITS
    FTFY
    0.71
    writeField
    0.69
     antaranya
    0.69
     condamné
    0.58
     lavorato
    0.57
    antaranya
    0.55
     présentés
    0.55
    ILayout
    0.54
     Inscrivez
    0.54
    外部連結
    0.53
    Activations Density 0.001%

    No Known Activations