© 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. 4667
    Prev
    Next
    INDEX
    Explanations

    standards and technical topics

    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
     estándar
    -0.75
     standards
    -0.73
     estándares
    -0.67
     standard
    -0.65
    standards
    -0.64
     Wiktionnaire
    -0.63
     Standards
    -0.61
    standard
    -0.61
     présidenti
    -0.60
     standaard
    -0.60
    POSITIVE LOGITS
    znamu
    0.47
    ásban
    0.46
     doInBackground
    0.46
     smite
    0.45
     pretend
    0.44
    enumi
    0.44
     MotionEvent
    0.44
    TagHelpers
    0.44
    verige
    0.43
     conjoint
    0.42
    Activations Density 0.008%

    No Known Activations