© 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. 4-CLT-HP
    7. 1496
    Prev
    Next
    INDEX
    Explanations

    &

    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
    reportWebVitals
    -0.39
     liitty
    -0.39
    .
    -0.35
     vägen
    -0.35
     larmes
    -0.34
     nemici
    -0.34
     oreilles
    -0.33
    mappedBy
    -0.32
    legung
    -0.32
    Legături
    -0.32
    POSITIVE LOGITS
    quot
    0.66
    daß
    0.63
    have
    0.60
    ideo
    0.59
    not
    0.59
    rise
    0.59
    tax
    0.58
     Have
    0.58
    let
    0.57
    safe
    0.57
    Activations Density 0.003%

    No Known Activations