© 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. 0-CLT-HP
    7. 42228
    Prev
    Next
    INDEX
    Explanations

    technical writing

    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
    MigrationBuilder
    -0.94
    oredCriteria
    -0.91
     Himo
    -0.81
    UnsafeEnabled
    -0.78
    OGND
    -0.73
     competence
    -0.68
    gonic
    -0.68
    ंदीखरीदारी
    -0.65
     Competence
    -0.65
    .*")]
    -0.64
    POSITIVE LOGITS
     dAtA
    0.46
    Seiten
    0.45
    Patterns
    0.44
    stick
    0.43
    es
    0.41
    cales
    0.41
    ages
    0.40
    sticks
    0.40
    s
    0.40
    AA
    0.39
    Activations Density 1.583%

    No Known Activations