© 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. 42376
    Prev
    Next
    INDEX
    Explanations

    scientific and technical subjects

    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
     beta
    -0.54
    s
    -0.52
     Matt
    -0.50
    sver
    -0.49
    casian
    -0.49
     Obrador
    -0.48
     Yard
    -0.48
     alpha
    -0.46
    ات
    -0.45
     Den
    -0.43
    POSITIVE LOGITS
    UnusedPrivate
    0.70
    ScopeManager
    0.65
     />\
    0.65
     sorella
    0.64
     pleaſure
    0.60
     myſelf
    0.59
     marito
    0.58
     houſe
    0.58
    igshid
    0.57
     occaf
    0.57
    Activations Density 0.090%

    No Known Activations