© 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. 0-CLT-HP
    7. 42199
    Prev
    Next
    INDEX
    Explanations

    technical/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
     Frankenstein
    -1.59
     cherchés
    -0.51
     cu
    -0.49
    ppens
    -0.47
    PLES
    -0.46
    dited
    -0.45
    INARY
    -0.45
    "%
    -0.45
     program
    -0.45
    ducation
    -0.45
    POSITIVE LOGITS
     Audiodateien
    0.79
    TemporalType
    0.71
     /\.
    0.70
     gambe
    0.70
     Wikispecies
    0.69
     createState
    0.69
     AssemblyCulture
    0.69
     tartalomajánló
    0.69
     fubject
    0.68
     FetchType
    0.67
    Activations Density 0.060%

    No Known Activations