© 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. 95116
    Prev
    Next
    INDEX
    Explanations

    writing or declaring

    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
    tagHelperRunner
    -0.67
    httphttps
    -0.64
     Baillargeon
    -0.63
     بيها
    -0.60
    __(/*!
    -0.59
     Paglinawan
    -0.58
    ⓧ
    -0.56
     distanciation
    -0.54
    addContainerGap
    -0.54
    addPreferredGap
    -0.54
    POSITIVE LOGITS
    ůli
    0.53
    redos
    0.52
     traj
    0.50
    JoinColumn
    0.49
     ground
    0.47
     VIN
    0.46
     wolle
    0.46
    +#+#
    0.45
     Spread
    0.45
     ioutil
    0.44
    Activations Density 0.381%

    No Known Activations