© 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. 4991
    Prev
    Next
    INDEX
    Explanations

    academic studies/data

    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
    AnchorStyles
    -0.78
    WebElementEntity
    -0.69
    InjectAttribute
    -0.64
    RegressionTest
    -0.64
    LookAnd
    -0.64
    LayoutParams
    -0.60
    bootstrapcdn
    -0.60
    stdc
    -0.60
     Мексичка
    -0.59
     modalités
    -0.59
    POSITIVE LOGITS
     some
    0.87
     many
    0.74
     several
    0.72
     previous
    0.72
     various
    0.70
     past
    0.67
     leading
    0.67
     the
    0.64
     different
    0.63
     certain
    0.63
    Activations Density 0.013%

    No Known Activations