© 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. 2860
    Prev
    Next
    INDEX
    Explanations

    yna

    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
     صوتيه
    -0.56
     demo
    -0.49
    GFR
    -0.48
    嘉
    -0.46
    Vii
    -0.45
     Vero
    -0.44
    __*/
    -0.43
     LOCK
    -0.43
    code
    -0.43
     demos
    -0.43
    POSITIVE LOGITS
     oprot
    0.71
     HttpNotFound
    0.70
    WillAppear
    0.70
    ArrowToggle
    0.67
     RouterModule
    0.66
    harusnya
    0.66
    providedIn
    0.65
    IonicModule
    0.63
     BrowserModule
    0.62
    ніципа
    0.60
    Activations Density 0.006%

    No Known Activations