© 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. 5-CLT-HP
    7. 979
    Prev
    Next
    INDEX
    Explanations

    Drawer

    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
     myſelf
    -0.91
     Paglinawan
    -0.90
     pleaſure
    -0.79
    хьтан
    -0.79
     purpoſe
    -0.77
     Савезне
    -0.74
     themſelves
    -0.73
    GEBURTS
    -0.72
     fubject
    -0.72
     cauſe
    -0.71
    POSITIVE LOGITS
    :
    0.84
    <eos>
    0.73
     :
    0.58
     disambiguazione
    0.54
    South
    0.53
    ResumeLayout
    0.51
     ibunya
    0.47
    micro
    0.46
     odeur
    0.45
    ;
    0.45
    Activations Density 0.020%

    No Known Activations