© 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. 76250
    Prev
    Next
    INDEX
    Explanations

    HTML Code

    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
     ModelExpression
    -0.83
     Audiodateien
    -0.67
    kuuta
    -0.64
    "}}>
    -0.58
    ectoria
    -0.57
    DataBind
    -0.55
     Coverage
    -0.54
     Legal
    -0.53
    ')))
    -0.52
    SerializedName
    -0.52
    POSITIVE LOGITS
    enumi
    0.52
    equilibrio
    0.46
     tvá
    0.46
     transposed
    0.45
    [:-
    0.45
    aprend
    0.45
     operativa
    0.45
     impregnated
    0.45
    hanging
    0.44
    ądź
    0.43
    Activations Density 0.001%

    No Known Activations