© 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. 43103
    Prev
    Next
    INDEX
    Explanations

    parenthesis

    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
    󠁿
    -0.80
    }{*}{}
    -0.59
    UVWXYZ
    -0.57
    ]**
    -0.56
    tôi
    -0.56
     PicClick
    -0.56
    WSGI
    -0.55
    .*/
    -0.54
    .}~\
    -0.54
    ugeot
    -0.53
    POSITIVE LOGITS
    0
    0.76
    2
    0.73
    7
    0.69
    ↵↵
    0.68
    1
    0.68
    The
    0.68
    6
    0.68
    K
    0.68
    5
    0.66
    3
    0.66
    Activations Density 0.232%

    No Known Activations