© 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. 90749
    Prev
    Next
    INDEX
    Explanations

    Electricity

    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
    bele
    -0.74
     nakalista
    -0.63
     blancs
    -0.59
     molecule
    -0.57
     découver
    -0.54
     régl
    -0.53
     découvertes
    -0.53
    FetchType
    -0.52
     idéia
    -0.50
    通販
    -0.49
    POSITIVE LOGITS
     purpoſe
    0.75
     raiſ
    0.74
     myſelf
    0.73
     ſtand
    0.71
    HomeAsUpEnabled
    0.68
    UnknownFields
    0.66
     Eſ
    0.63
     Majefty
    0.63
     anſ
    0.62
     himſelf
    0.61
    Activations Density 0.470%

    No Known Activations