© 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. 8817
    Prev
    Next
    INDEX
    Explanations

    a

    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
    Negative Logits
     controllers
    -0.65
    agers
    -0.57
     poussière
    -0.56
     dignité
    -0.55
    ulators
    -0.54
    IDENTS
    -0.54
     carriers
    -0.52
     betweenstory
    -0.52
    ians
    -0.52
     attackers
    -0.52
    POSITIVE LOGITS
    SequentialGroup
    0.68
    stateProvider
    0.66
    AnimationsModule
    0.64
     person
    0.63
    osoba
    0.61
    NullCheck
    0.59
     guy
    0.59
     boy
    0.57
     soldier
    0.57
    Obrázky
    0.57
    Activations Density 0.010%

    No Known Activations