© 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. 9988
    Prev
    Next
    INDEX
    Explanations

    being probable

    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
    StoryboardSegue
    -0.95
     الحره
    -0.93
    delwed
    -0.85
    ArgsConstructor
    -0.84
     Савезне
    -0.84
     disambiguazione
    -0.76
    OGND
    -0.75
     lenker
    -0.73
    phemy
    -0.73
     محفوظة
    -0.70
    POSITIVE LOGITS
     be
    0.65
     needed
    0.63
     experience
    0.56
     only
    0.54
     necessary
    0.53
    zut
    0.52
     indicated
    0.52
    原
    0.52
     failed
    0.51
     need
    0.50
    Activations Density 0.017%

    No Known Activations