© 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. 0-CLT-HP
    7. 94429
    Prev
    Next
    INDEX
    Explanations

    maxillary

    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
    iden
    -0.59
    Portale
    -0.53
    IVEREF
    -0.52
    quid
    -0.49
    rzost
    -0.49
     Glo
    -0.48
    стасия
    -0.47
     Imp
    -0.45
    IDEN
    -0.44
    aClass
    -0.44
    POSITIVE LOGITS
     فريبيس
    0.76
     חיצוניים
    0.73
     Obtenez
    0.70
    numerusform
    0.69
    principalColumn
    0.69
    Eksteraj
    0.68
    })));
    0.68
    rostis
    0.67
    tagHelperRunner
    0.64
    Viited
    0.63
    Activations Density 0.325%

    No Known Activations