© 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. 76104
    Prev
    Next
    INDEX
    Explanations

    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
    LS
    -0.61
    LG
    -0.60
    DB
    -0.59
    KB
    -0.58
    TE
    -0.58
    SE
    -0.58
    JT
    -0.58
    PK
    -0.57
    RB
    -0.57
    SK
    -0.57
    POSITIVE LOGITS
     AssemblyCulture
    0.42
    DockStyle
    0.41
    ]")]
    0.40
     AssemblyProduct
    0.39
     Rid
    0.39
    ContentAsync
    0.36
     Mid
    0.36
    pdev
    0.35
    ConstraintMaker
    0.35
     Herr
    0.35
    Activations Density 0.037%

    No Known Activations