© 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. 1-CLT-HP
    7. 15524
    Prev
    Next
    INDEX
    Explanations

    needed/necessary

    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
     honored
    -0.68
     favorable
    -0.67
    '));
    -0.66
     Theaters
    -0.65
    Theater
    -0.63
    FAVOR
    -0.63
     theater
    -0.63
    ']);
    -0.62
    favorable
    -0.62
     createSlice
    -0.61
    POSITIVE LOGITS
    ंदीखरीदारी
    0.47
    VIAF
    0.45
     autorytatywna
    0.45
    RenderAtEndOf
    0.42
     items
    0.42
     cáo
    0.42
    uelva
    0.41
     space
    0.41
    retan
    0.40
    items
    0.40
    Activations Density 0.011%

    No Known Activations