© 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. 20-CLT-HP
    7. 72336
    Prev
    Next
    INDEX
    Explanations

    code

    np_max-act-logits · 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
     port
    -0.46
    ULING
    -0.45
     "
    -0.44
     esp
    -0.44
    }{*}{
    -0.42
     ber
    -0.42
     “
    -0.42
     lluvia
    -0.42
    eaks
    -0.40
    poort
    -0.40
    POSITIVE LOGITS
     ſche
    1.03
     auffi
    0.99
     pleaſure
    0.98
     Majefty
    0.98
     Houſe
    0.98
     Theſe
    0.97
     propOrder
    0.96
     ―――――
    0.96
    LookAnd
    0.96
     Efq
    0.95
    Activations Density 0.004%

    No Known Activations