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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-CLT-HP
    7. 3273
    Prev
    Next
    INDEX
    Explanations

    not

    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
    IMPORTED
    -0.60
    withIdentifier
    -0.58
     épaules
    -0.57
     proposées
    -0.55
     médec
    -0.54
     framed
    -0.52
     født
    -0.52
     mogelijk
    -0.51
     antaranya
    -0.51
    ioutil
    -0.51
    POSITIVE LOGITS
    rungsseite
    0.77
     CommonModule
    0.55
     autorytatywna
    0.54
     дописавши
    0.54
     kaarangay
    0.52
    LabelTagHelper
    0.50
     Biôgrafia
    0.47
    Legături
    0.47
     bets
    0.46
    */}
    0.46
    Activations Density 0.003%

    No Known Activations