© 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. 20-CLT-HP
    7. 76711
    Prev
    Next
    INDEX
    Explanations

    technical

    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
     bpy
    -0.63
    帖最后由
    -0.60
    PMC
    -0.60
    ghed
    -0.59
    <bos>
    -0.59
    èdia
    -0.58
    AppMethodBeat
    -0.56
    addCriterion
    -0.56
    sterone
    -0.56
     Mako
    -0.56
    POSITIVE LOGITS
    UserScript
    0.54
    EnableWeb
    0.51
    printLine
    0.41
    CloseOperation
    0.40
    ForRow
    0.39
    InitVars
    0.39
     Hi
    0.37
    SceneManagement
    0.37
    UnknownFieldSet
    0.36
    IsMutable
    0.36
    Activations Density 0.001%

    No Known Activations