© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 0-CLT-HP
    4. 39784
    Prev
    Next
    INDEX
    Explanations

    miscellaneous articles

    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
     Theſe
    -1.46
     ſeveral
    -1.39
     myſelf
    -1.38
     purpoſe
    -1.36
     Monfieur
    -1.35
     houſe
    -1.34
     himſelf
    -1.32
     whoſe
    -1.30
     poffible
    -1.26
     uſe
    -1.23
    POSITIVE LOGITS
     As
    0.69
     We
    0.67
     In
    0.64
     Pro
    0.59
     Read
    0.56
    <eos>
    0.55
     B
    0.55
     A
    0.54
     All
    0.53
     Lab
    0.52
    Activations Density 1.556%

    No Known Activations