© 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. 9027
    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
    DataAnnotations
    -0.63
     guerres
    -0.53
     förr
    -0.53
     refirió
    -0.53
     eenige
    -0.53
    coarse
    -0.52
     casó
    -0.52
     feroit
    -0.52
     eenig
    -0.51
     auroit
    -0.51
    POSITIVE LOGITS
    line
    0.53
    DllImport
    0.51
    wards
    0.50
    ward
    0.50
    ness
    0.47
    ancy
    0.46
    nell
    0.45
    isy
    0.45
    board
    0.45
    reci
    0.45
    Activations Density 0.030%

    No Known Activations