© 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. 1-CLT-HP
    7. 14714
    Prev
    Next
    INDEX
    Explanations

    guides and documentation

    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
     pengguna
    -0.59
     user
    -0.54
    +#+#
    -0.45
     User
    -0.45
     setUser
    -0.43
    onymus
    -0.43
    Spaces
    -0.41
    kranz
    -0.41
     initWithFrame
    -0.41
     деле
    -0.41
    POSITIVE LOGITS
     الحره
    0.75
     مرئيه
    0.67
     EoL
    0.67
    RectangleBorder
    0.66
    AndEndTag
    0.64
     Réponses
    0.64
    Билгалдахарш
    0.61
    StoryboardSegue
    0.60
     فريبيس
    0.59
     taint
    0.59
    Activations Density 0.071%

    No Known Activations