© 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. 91251
    Prev
    Next
    INDEX
    Explanations

    questions

    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
    tvguidetime
    -0.64
    ::$
    -0.60
    IsContent
    -0.52
    TagHelpers
    -0.52
    contentLoaded
    -0.50
     dé
    -0.50
    ionais
    -0.49
    styleable
    -0.49
    ariable
    -0.47
    .”
    -0.46
    POSITIVE LOGITS
    ArrowToggle
    0.64
    ApiModelProperty
    0.61
    __(/*!
    0.59
    argout
    0.57
     beginnetje
    0.57
    MigrationBuilder
    0.57
    DataPropertyName
    0.56
     Chwiliwch
    0.54
    setGeometry
    0.52
    tagHelperRunner
    0.51
    Activations Density 0.065%

    No Known Activations