© 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. 0-CLT-HP
    7. 39961
    Prev
    Next
    INDEX
    Explanations

    {

    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
    itio
    -0.56
     Ause
    -0.55
     مرئيه
    -0.55
     sub
    -0.53
     Boyer
    -0.53
    enumii
    -0.51
     self
    -0.50
    exec
    -0.50
    ंदीखरीदारी
    -0.49
    题
    -0.49
    POSITIVE LOGITS
     nascita
    0.70
    AutoScaleMode
    0.66
     blessés
    0.66
     originaux
    0.64
     stampa
    0.63
     giornal
    0.63
     devenus
    0.62
     popoli
    0.60
     viendra
    0.60
     vectorielles
    0.60
    Activations Density 1.664%

    No Known Activations