© 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. 42565
    Prev
    Next
    INDEX
    Explanations

    Crusade

    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
     BoxFit
    -0.65
    Normdaten
    -0.64
    Portale
    -0.60
    spreis
    -0.60
    Rüyada
    -0.59
    azzo
    -0.59
    Hochspringen
    -0.59
    Lähteet
    -0.58
    NameInMap
    -0.57
    charis
    -0.57
    POSITIVE LOGITS
     cucchia
    0.65
     alluminio
    0.59
     européennes
    0.58
     besluit
    0.57
     étoit
    0.57
     médicaux
    0.57
     morire
    0.56
     panoramique
    0.53
     creș
    0.52
     étoient
    0.52
    Activations Density 0.241%

    No Known Activations