© 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. 5-CLT-HP
    7. 91656
    Prev
    Next
    INDEX
    Explanations

    Proper nouns/code snippets

    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
     Efq
    -1.17
     Majefty
    -1.01
     Jefus
    -1.01
     Monfieur
    -0.96
     purpoſe
    -0.95
     ſche
    -0.94
     ſtate
    -0.92
     neceffary
    -0.90
     fhew
    -0.90
     pleaf
    -0.89
    POSITIVE LOGITS
    <bos>
    0.94
    '
    0.60
     get
    0.59
     so
    0.57
     "
    0.57
     “
    0.56
     ma
    0.54
     that
    0.53
     on
    0.52
     van
    0.52
    Activations Density 0.532%

    No Known Activations