© 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. 5-CLT-HP
    7. 4627
    Prev
    Next
    INDEX
    Explanations

    maintenance/code

    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
     defaultstate
    -0.73
    UnknownFields
    -0.72
    VersionUID
    -0.69
    niająca
    -0.68
    orianCalendar
    -0.67
     فريبيس
    -0.67
    InjectAttribute
    -0.66
    rrggbb
    -0.66
     nakalista
    -0.63
    apunov
    -0.63
    POSITIVE LOGITS
     correctly
    0.45
     sportivo
    0.44
     conséquences
    0.44
     råd
    0.44
     suivant
    0.43
     μή
    0.42
     Celui
    0.42
    niosek
    0.41
    bumptech
    0.41
    },"
    0.40
    Activations Density 0.002%

    No Known Activations