© 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. 94002
    Prev
    Next
    INDEX
    Explanations

    production

    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
    tw
    -0.47
     product
    -0.46
    ัด
    -0.45
    ing
    -0.45
    alve
    -0.41
     aigu
    -0.40
    lington
    -0.40
    ähkö
    -0.40
     BRON
    -0.39
    ########.
    -0.39
    POSITIVE LOGITS
     propOrder
    0.96
     '\\;'
    0.89
     Normdatei
    0.86
    AndEndTag
    0.85
     ExecuteAsync
    0.79
    ukone
    0.78
    GEBURTSDATUM
    0.78
    ResumeLayout
    0.78
    tagHelperRunner
    0.76
    ValueStyle
    0.75
    Activations Density 0.086%

    No Known Activations