© 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. 20-CLT-HP
    7. 73472
    Prev
    Next
    INDEX
    Explanations

    various technical and foreign texts

    np_max-act-logits · 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
    writeField
    -0.68
    EndTag
    -0.59
    Sklici
    -0.58
    хьтан
    -0.58
    Portail
    -0.57
    évaluateur
    -0.57
    IBarButtonItem
    -0.57
    AndEndTag
    -0.57
    expandindo
    -0.57
     مشين
    -0.57
    POSITIVE LOGITS
    poel
    0.46
     فريبيس
    0.46
    μι
    0.46
    CGRectMake
    0.44
    коном
    0.44
     belas
    0.43
     Sok
    0.41
    mach
    0.41
     Stad
    0.41
    wyl
    0.41
    Activations Density 0.000%

    No Known Activations