© 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. 5-CLT-HP
    7. 5813
    Prev
    Next
    INDEX
    Explanations

    action verbs and causation

    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
     möjligt
    -0.65
     bäst
    -0.61
    конец
    -0.55
     snabb
    -0.54
    kjø
    -0.54
     automatiques
    -0.54
    reszcie
    -0.53
     BoxDecoration
    -0.52
    XmlAccessorType
    -0.49
     visibilité
    -0.49
    POSITIVE LOGITS
    IBOutlet
    0.68
    ModelAdmin
    0.65
     onCancelled
    0.61
    StreetMap
    0.58
    WebElementEntity
    0.56
    ImageContext
    0.56
    Abitanti
    0.55
     Signalez
    0.55
    kháu
    0.55
     snippetHide
    0.54
    Activations Density 0.008%

    No Known Activations