© 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
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 1509
    Prev
    Next
    INDEX
    Explanations

    held

    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
     Caster
    -0.63
     Cast
    -0.60
     caster
    -0.57
    Cast
    -0.56
     doInBackground
    -0.56
     caste
    -0.56
     Caste
    -0.53
    Caster
    -0.49
     potere
    -0.48
    Past
    -0.47
    POSITIVE LOGITS
    s
    0.90
    er
    0.78
    ities
    0.65
    ed
    0.63
    aine
    0.61
    erda
    0.61
    किन
    0.60
    ergies
    0.58
    SCAPE
    0.57
    eries
    0.57
    Activations Density 1.169%

    No Known Activations