© 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. 0-CLT-HP
    7. 93466
    Prev
    Next
    INDEX
    Explanations

    girl

    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
     '\\;'
    -0.71
     OFDb
    -0.71
    StoryboardSegue
    -0.71
     ſch
    -0.68
     Jefus
    -0.66
     pleaſure
    -0.65
     industriale
    -0.64
     Ababa
    -0.64
     tuyo
    -0.62
     tranſ
    -0.62
    POSITIVE LOGITS
    HasAnnotation
    0.56
    ’
    0.54
    /*
    0.53
     you
    0.52
     providing
    0.50
     bringing
    0.48
     he
    0.47
     invokingState
    0.46
     nahilalakip
    0.45
     we
    0.45
    Activations Density 0.124%

    No Known Activations