© 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. 93922
    Prev
    Next
    INDEX
    Explanations

    will

    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
    DockStyle
    -1.12
     Савезне
    -1.02
     doubtnut
    -0.99
    ValueStyle
    -0.98
     myſelf
    -0.91
     سكانية
    -0.90
    rrggbb
    -0.89
     fevere
    -0.89
    IVEREF
    -0.88
    فایل‌لار
    -0.87
    POSITIVE LOGITS
     be
    0.67
     all
    0.62
    se
    0.58
    <bos>
    0.54
    be
    0.52
     his
    0.51
     See
    0.50
     cost
    0.49
    See
    0.47
     see
    0.47
    Activations Density 0.022%

    No Known Activations