© 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. 1393
    Prev
    Next
    INDEX
    Explanations

    with

    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
     the
    -0.69
     this
    -0.52
     all
    -0.51
     every
    -0.47
     key
    -0.43
     increased
    -0.43
     and
    -0.42
     todas
    -0.42
    postmedia
    -0.41
     how
    -0.39
    POSITIVE LOGITS
    WebElementEntity
    0.95
     gynhyrchwyd
    0.91
    Personensuche
    0.85
    intios
    0.82
     CURIAM
    0.76
    GEBURTSDATUM
    0.75
    setVerticalGroup
    0.75
    rungsseite
    0.75
     balloons
    0.74
     crickets
    0.74
    Activations Density 0.011%

    No Known Activations