© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 97337
    Prev
    Next
    INDEX
    Explanations

    of

    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
    abstractmethod
    -0.58
    Árbitro
    -0.57
     transacción
    -0.57
    ējās
    -0.55
    cheibe
    -0.54
    aronder
    -0.54
    interpreter
    -0.54
    IntoConstraints
    -0.54
    ógrafo
    -0.54
    uksessa
    -0.54
    POSITIVE LOGITS
     Creation
    0.58
     utafitiHapana
    0.58
    VersionUID
    0.54
     Existence
    0.49
     existence
    0.48
     ***!
    0.48
     creation
    0.48
     Relationship
    0.47
    Existence
    0.47
    existence
    0.46
    Activations Density 0.000%

    No Known Activations