© 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
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 92050
    Prev
    Next
    INDEX
    Explanations

    scientific texts

    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
     g
    -0.74
     
    -0.66
     Number
    -0.65
    ,
    -0.59
     in
    -0.58
     min
    -0.57
    ↵↵
    -0.54
    ↵
    -0.54
     Mall
    -0.50
    ↵↵↵
    -0.50
    POSITIVE LOGITS
     Efq
    1.10
     itſelf
    1.10
     raiſ
    1.09
     Theſe
    1.07
     myſelf
    1.07
    ſelves
    1.06
     uſe
    1.04
     pleaſure
    1.04
     uſed
    1.03
     themſelves
    1.00
    Activations Density 0.269%

    No Known Activations