© 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. 42876
    Prev
    Next
    INDEX
    Explanations

    language

    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
     propOrder
    -0.79
    tagHelperRunner
    -0.71
     متعلقه
    -0.68
     disponibilités
    -0.68
    addPreferredGap
    -0.67
    antaranya
    -0.67
     särskilt
    -0.67
    ContentLoaded
    -0.62
    ConstraintMaker
    -0.60
    withstanding
    -0.60
    POSITIVE LOGITS
     Semantics
    0.53
     Silverman
    0.52
     languages
    0.49
     Epidemiology
    0.49
     squamous
    0.49
     Shah
    0.48
     speech
    0.47
     Scalar
    0.47
     semantics
    0.47
    scal
    0.47
    Activations Density 0.064%

    No Known Activations