© 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. 42753
    Prev
    Next
    INDEX
    Explanations

    quote character

    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
     ‘
    -0.97
     “
    -0.83
    .’
    -0.75
     «
    -0.70
     \\
    -0.65
     ’
    -0.65
     „
    -0.65
    …
    -0.64
    ’.
    -0.63
    …’
    -0.63
    POSITIVE LOGITS
    <em>
    0.82
    <strong>
    0.81
    <b>
    0.66
     negru
    0.60
     picioare
    0.60
     pitié
    0.60
     noastre
    0.59
     Majefty
    0.59
     chrétien
    0.59
     financeiro
    0.59
    Activations Density 0.002%

    No Known Activations