© 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. 43170
    Prev
    Next
    INDEX
    Explanations

    Code/templates

    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
    υτό
    -0.48
    Muri
    -0.46
    RegressionTest
    -0.46
    assas
    -0.43
    fois
    -0.42
     Maurer
    -0.41
     vyst
    -0.41
    wildcard
    -0.41
     controversi
    -0.40
    след
    -0.40
    POSITIVE LOGITS
    XmlAccessType
    0.77
    findpost
    0.72
    +#+#
    0.70
    帖最后由
    0.67
    ($__
    0.66
    GraphicsUnit
    0.65
    TagHelper
    0.65
    AndEndTag
    0.64
     linkovi
    0.64
     ostavi
    0.63
    Activations Density 0.130%

    No Known Activations