© 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. 40165
    Prev
    Next
    INDEX
    Explanations

    URLs and code repositories

    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
     York
    -0.80
    ess
    -0.74
     YORK
    -0.64
     york
    -0.61
    York
    -0.58
    CP
    -0.57
    youtube
    -0.56
    ctions
    -0.54
     bowl
    -0.53
    CTIONS
    -0.53
    POSITIVE LOGITS
     ―――――
    0.77
     raiſ
    0.77
     Anſ
    0.76
     pleaſure
    0.76
     Houſe
    0.74
     Inſ
    0.74
     Efq
    0.74
     Monfieur
    0.74
     ſche
    0.72
     Theſe
    0.72
    Activations Density 0.421%

    No Known Activations