© 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. 93628
    Prev
    Next
    INDEX
    Explanations

    existing

    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
     existing
    -2.27
    existing
    -2.16
     Existing
    -1.63
    Existing
    -1.62
     bestaande
    -1.49
     existentes
    -1.44
     EXISTING
    -1.40
     существу
    -1.36
     bestehenden
    -1.35
     existente
    -1.34
    POSITIVE LOGITS
    出版年
    0.83
    __*/
    0.71
    ValueStyle
    0.58
    utched
    0.58
    casus
    0.58
     doInBackground
    0.58
    ⏜
    0.57
     nakalista
    0.57
    ToProps
    0.56
     okuyayım
    0.56
    Activations Density 0.016%

    No Known Activations