© 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. 4-CLT-HP
    7. 569
    Prev
    Next
    INDEX
    Explanations

    free

    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
    hability
    -0.51
    sure
    -0.50
    standing
    -0.50
    sista
    -0.50
     externi
    -0.49
     purpoſe
    -0.49
     nghiệp
    -0.47
    migrationBuilder
    -0.47
    raj
    -0.47
    content
    -0.45
    POSITIVE LOGITS
    ❋
    0.62
     Paglinawan
    0.56
     pratiquer
    0.55
     AssemblyCompany
    0.54
    AntiForgeryToken
    0.54
    发表于
    0.52
     descendre
    0.52
     CanadaChoose
    0.52
    TypedDataSet
    0.51
     navires
    0.51
    Activations Density 0.044%

    No Known Activations