© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 97615
    Prev
    Next
    INDEX
    Explanations

    also

    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
     other
    -0.60
    的其他
    -0.57
    else
    -0.56
     Other
    -0.56
     Another
    -0.55
    Other
    -0.50
     another
    -0.47
    another
    -0.47
     otro
    -0.47
    ']));
    -0.47
    POSITIVE LOGITS
     مشين
    1.01
    <bos>
    0.90
    évaluateur
    0.90
    Personensuche
    0.89
     '\\;'
    0.87
    ConstraintMaker
    0.87
    +#+#
    0.86
    GOTREF
    0.86
     nahilalakip
    0.85
    tagHelperRunner
    0.84
    Activations Density 0.177%

    No Known Activations