© 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. 92920
    Prev
    Next
    INDEX
    Explanations

    ter

    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
    >{@
    -0.60
     to
    -0.57
    ,
    -0.53
    XDECREF
    -0.52
     IConfiguration
    -0.50
     in
    -0.49
    semibold
    -0.49
     of
    -0.49
     referred
    -0.48
     and
    -0.47
    POSITIVE LOGITS
    ſelves
    0.75
     Reſ
    0.68
    pless
    0.66
    standers
    0.65
    pois
    0.64
    ſelf
    0.64
    lling
    0.62
     Diſ
    0.60
    psy
    0.59
    edly
    0.59
    Activations Density 0.036%

    No Known Activations