© 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. 92452
    Prev
    Next
    INDEX
    Explanations

    organizations or teams

    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
    <bos>
    -0.63
     Réponses
    -0.55
     aston
    -0.54
     lccn
    -0.53
     cordially
    -0.53
    ’
    -0.53
    '
    -0.52
     yolk
    -0.51
     romaine
    -0.50
     purtroppo
    -0.50
    POSITIVE LOGITS
    ändler
    0.63
    antMatchers
    0.60
    csolódó
    0.59
    __*/
    0.56
    antaine
    0.54
     CITED
    0.54
    ecé
    0.54
    addGap
    0.53
    paravant
    0.53
    mentions
    0.53
    Activations Density 0.036%

    No Known Activations