© 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. 43206
    Prev
    Next
    INDEX
    Explanations

    fundamental knowledge

    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
     basics
    -1.99
    basics
    -1.82
    Basics
    -1.81
    basic
    -1.79
     basic
    -1.76
    Basic
    -1.70
     Basic
    -1.61
     Basics
    -1.60
    BASIC
    -1.52
     BASIC
    -1.49
    POSITIVE LOGITS
     for
    0.57
    ,
    0.56
     in
    0.56
     and
    0.56
     of
    0.52
     such
    0.52
     like
    0.49
    hift
    0.47
    catchError
    0.44
     gained
    0.44
    Activations Density 0.151%

    No Known Activations