© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-CLT-HP
    7. 2735
    Prev
    Next
    INDEX
    Explanations

    diverse internet text

    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
    erstein
    -0.52
     Drucker
    -0.50
    éri
    -0.48
    LOYE
    -0.47
     vPvB
    -0.47
    locked
    -0.47
    rena
    -0.47
    ereich
    -0.46
    extendable
    -0.46
    feasible
    -0.46
    POSITIVE LOGITS
    <bos>
    1.03
     ModelExpression
    0.73
    ⓧ
    0.63
     continúas
    0.62
    GEBURTSDATUM
    0.60
     calendriers
    0.57
    Климат
    0.56
    WebVitals
    0.56
     BoxFit
    0.49
     cards
    0.47
    Activations Density 0.008%

    No Known Activations