© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 0-CLT-HP
    4. 45389
    Prev
    Next
    INDEX
    Explanations

    Scientific and technical texts

    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
    GEBURTSDATUM
    -0.92
    featureID
    -0.89
     soul
    -0.84
    +#+
    -0.82
    endphp
    -0.75
     Nerv
    -0.74
     Soul
    -0.73
    ModelAdmin
    -0.72
     barrel
    -0.72
    fony
    -0.70
    POSITIVE LOGITS
    s
    0.92
    smith
    0.60
    sent
    0.53
    an
    0.52
    san
    0.49
    ans
    0.48
    ar
    0.47
    schen
    0.47
    at
    0.47
    ся
    0.46
    Activations Density 0.078%

    No Known Activations