© 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. 4-CLT-HP
    7. 750
    Prev
    Next
    INDEX
    Explanations

    intent

    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
    actionMode
    -0.58
     Vikipedi
    -0.52
    LError
    -0.52
    expandindo
    -0.51
    : 
    -0.47
     religieuses
    -0.47
    reportWebVitals
    -0.46
    Portale
    -0.46
    cionais
    -0.45
    cookieParser
    -0.45
    POSITIVE LOGITS
     consultato
    0.63
     cropping
    0.58
     renting
    0.58
    PreAuthorize
    0.55
     slapping
    0.55
    日発売
    0.53
     beating
    0.53
    imageshack
    0.52
     selling
    0.52
    SourceChecksum
    0.52
    Activations Density 0.004%

    No Known Activations