© 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. 1-CLT-HP
    7. 668
    Prev
    Next
    INDEX
    Explanations

    fact

    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
     crí
    -0.60
     fact
    -0.59
    ματο
    -0.56
    fact
    -0.55
    </thead>
    -0.54
     насељу
    -0.53
    __',
    -0.53
    \"");
    -0.52
    事实
    -0.49
    GINS
    -0.49
    POSITIVE LOGITS
     contextLoads
    0.66
    Obrázky
    0.63
     FontFamily
    0.59
    WritableDatabase
    0.58
     considérons
    0.57
    Nazionale
    0.56
     implants
    0.56
    يميديا
    0.54
    bootstrapcdn
    0.54
     vegetarians
    0.53
    Activations Density 0.074%

    No Known Activations