© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 91206
    Prev
    Next
    INDEX
    Explanations

    the, whether

    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
     Chwiliwch
    -0.66
     án
    -0.65
     utafitiHapana
    -0.62
    ցված
    -0.60
     متعلقه
    -0.60
    OGND
    -0.59
     autorytatywna
    -0.57
    EndProject
    -0.56
     SQLAlchemy
    -0.56
    BindingResult
    -0.56
    POSITIVE LOGITS
    Архівовано
    0.48
     lar
    0.48
    lankton
    0.47
    pă
    0.47
    DebuggerNonUser
    0.46
     jsPsych
    0.46
    Geplaatst
    0.45
    EndInit
    0.45
    Either
    0.44
     either
    0.44
    Activations Density 0.015%

    No Known Activations