© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 20-CLT-HP
    7. 71860
    Prev
    Next
    INDEX
    Explanations

    Technical/scientific 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
    Espèce
    -0.69
    ″]
    -0.69
     Wiktionnaire
    -0.68
     myſelf
    -0.66
    providedIn
    -0.66
     Oggi
    -0.66
     GenerationType
    -0.65
    tomas
    -0.65
     AssemblyCulture
    -0.65
     referenties
    -0.64
    POSITIVE LOGITS
    بوابة
    0.49
     spoko
    0.40
     xảy
    0.38
    ("../../
    0.38
     paramInt
    0.37
    (",");
    0.36
    +".
    0.34
    xi
    0.33
    ój
    0.33
    ernos
    0.33
    Activations Density 0.001%

    No Known Activations