© 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. 73436
    Prev
    Next
    INDEX
    Explanations

    Code, names, and nouns

    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
     lenker
    -0.66
    Geplaatst
    -0.65
    EDEFAULT
    -0.58
     StatefulWidget
    -0.58
     Metcalf
    -0.57
     ErrIntOverflow
    -0.56
     unknownFields
    -0.55
    WaitGroup
    -0.54
    पया
    -0.54
    ineno
    -0.53
    POSITIVE LOGITS
    OrNil
    0.52
    orme
    0.48
    OR
    0.47
    AddTagHelper
    0.47
    orb
    0.46
    orce
    0.45
    ApiModelProperty
    0.45
    orii
    0.44
    ORS
    0.43
     שוליים
    0.42
    Activations Density 0.000%

    No Known Activations