© 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. 0-CLT-HP
    7. 41268
    Prev
    Next
    INDEX
    Explanations

    absor

    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
    sd
    -0.72
    lig
    -0.64
     isSet
    -0.59
     Gifford
    -0.56
    LookAnd
    -0.55
     sucks
    -0.54
    mock
    -0.53
    \}\\
    -0.52
    cted
    -0.50
    tified
    -0.49
    POSITIVE LOGITS
     calyx
    0.63
     évêque
    0.61
     gully
    0.61
    Personendaten
    0.60
    hirts
    0.60
     plagioclase
    0.59
     Legendre
    0.59
     Extragalactic
    0.59
    InputTagHelper
    0.58
     Cientí
    0.58
    Activations Density 0.095%

    No Known Activations