© 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. 5-CLT-HP
    7. 94026
    Prev
    Next
    INDEX
    Explanations

    sweaty

    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
     preuves
    -0.64
     principaux
    -0.63
     متعلقه
    -0.63
     förr
    -0.62
     cérami
    -0.62
     calendriers
    -0.61
     Grecs
    -0.58
     jouets
    -0.57
    väg
    -0.57
     feroit
    -0.57
    POSITIVE LOGITS
    ness
    0.68
     looking
    0.59
     vibes
    0.59
     ideas
    0.59
     feelings
    0.58
     aspects
    0.57
     appearances
    0.55
    looking
    0.55
     appearance
    0.54
     visuals
    0.54
    Activations Density 0.000%

    No Known Activations