© 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. 20-CLT-HP
    7. 75755
    Prev
    Next
    INDEX
    Explanations

    research/technical texts

    np_max-act-logits · 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
     phép
    -0.58
    出版年
    -0.57
    IsContent
    -0.54
     *)__
    -0.54
    setopt
    -0.52
     Réponses
    -0.50
    TabStop
    -0.50
     bevis
    -0.47
    GHIJKLM
    -0.46
    ⚕
    -0.46
    POSITIVE LOGITS
     Information
    0.60
    Legenda
    0.57
    Information
    0.56
     Roskov
    0.56
     information
    0.54
     Higher
    0.53
    Higher
    0.53
    information
    0.53
     HCI
    0.53
     Net
    0.52
    Activations Density 0.001%

    No Known Activations