© 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. 45553
    Prev
    Next
    INDEX
    Explanations

    Nog

    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
     Schrödinger
    -1.45
    SDL
    -0.92
    VersionUID
    -0.86
     myſelf
    -0.84
     SDL
    -0.81
     ſmall
    -0.81
     purpoſe
    -0.79
     Etrus
    -0.79
     itſelf
    -0.77
     pleaſure
    -0.74
    POSITIVE LOGITS
     kon
    0.49
     pod
    0.47
     per
    0.47
     zak
    0.47
     pro
    0.46
     vis
    0.45
     pe
    0.45
     ro
    0.44
     pr
    0.44
     casual
    0.43
    Activations Density 0.101%

    No Known Activations