© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 41918
    Prev
    Next
    INDEX
    Explanations

    Unexpected events and technical functionalities

    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
    bewerken
    -0.76
    WebVitals
    -0.70
    StoryboardSegue
    -0.67
    Parcelize
    -0.66
     nakalista
    -0.64
    mtrl
    -0.63
    ...");
    -0.63
     OMITTED
    -0.59
     BrowserModule
    -0.59
    InjectAttribute
    -0.59
    POSITIVE LOGITS
    χο
    0.48
    ы
    0.46
    帖最后由
    0.45
    pressor
    0.44
    ukone
    0.44
    gering
    0.43
    znik
    0.43
    uría
    0.43
    iesis
    0.43
     nahilalakip
    0.43
    Activations Density 0.147%

    No Known Activations