© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 4760
    Prev
    Next
    INDEX
    Explanations

    and

    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
    StoryboardSegue
    -0.84
    EndContext
    -0.79
     other
    -0.76
    Trama
    -0.74
     useAppContext
    -0.73
     photolibrary
    -0.71
    cheibe
    -0.71
    ̀
    -0.71
    createTextNode
    -0.69
     endregion
    -0.69
    POSITIVE LOGITS
     otomatig
    0.37
    Autoritní
    0.37
    protoimpl
    0.32
    ärin
    0.30
     fá
    0.29
     pelota
    0.29
    WindowConstants
    0.28
    .
    0.28
     and
    0.28
    ASK
    0.28
    Activations Density 0.013%

    No Known Activations