© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26
    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 5-CLT-HP
    4. 91124
    Prev
    Next
    INDEX
    Explanations

    document metadata/headers

    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
    </em>
    -0.51
    ')).
    -0.49
    },
    -0.47
    exactly
    -0.46
    ()][
    -0.46
     pří
    -0.45
    !")
    -0.44
    )),
    -0.44
    ),"
    -0.44
    »,
    -0.44
    POSITIVE LOGITS
    enumi
    0.92
    RectangleBorder
    0.86
     AssemblyCulture
    0.82
     ſtre
    0.77
     الرياضيه
    0.73
    ngdoc
    0.72
     purpoſe
    0.71
    enumii
    0.71
    ISupport
    0.70
     himſelf
    0.69
    Activations Density 0.030%

    No Known Activations