© 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. 1-CLT-HP
    7. 15927
    Prev
    Next
    INDEX
    Explanations

    military operations

    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
    <bos>
    -0.90
    المكان
    -0.53
    As
    -0.50
     As
    -0.48
     K
    -0.47
    UnitTesting
    -0.47
    SuppressLint
    -0.46
    Configurer
    -0.45
     Absch
    -0.44
    CodeAttribute
    -0.43
    POSITIVE LOGITS
    GEBURTSDATUM
    0.84
     OFDb
    0.63
     littéraire
    0.62
    UserScript
    0.61
    Obrázky
    0.60
    CDATA
    0.59
    chowy
    0.58
    transQ
    0.58
     célè
    0.57
    getComponent
    0.56
    Activations Density 0.011%

    No Known Activations