© 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. 5-CLT-HP
    7. 93092
    Prev
    Next
    INDEX
    Explanations

    code or jumbled text

    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
     gynhyrchwyd
    -0.81
    RenderAtEndOf
    -0.79
     يتيمه
    -0.67
    EndInit
    -0.65
    énario
    -0.61
    Hochspringen
    -0.60
     "..\..\
    -0.59
     ModelExpression
    -0.58
     Kuri
    -0.58
     חיצוניים
    -0.57
    POSITIVE LOGITS
    les
    0.59
    ls
    0.57
    l
    0.56
    UnknownFields
    0.47
    lma
    0.46
    pirable
    0.46
    scope
    0.45
    boh
    0.44
    ols
    0.43
    <!--[
    0.42
    Activations Density 0.005%

    No Known Activations