© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 93639
    Prev
    Next
    INDEX
    Explanations

    text fragments and abbreviations

    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
    igshid
    -0.79
     مشين
    -0.75
    出版年
    -0.70
    featureID
    -0.70
    Референце
    -0.67
    Problems
    -0.67
    providedIn
    -0.67
    >{@
    -0.66
     Solutions
    -0.65
    kloped
    -0.65
    POSITIVE LOGITS
    saludos
    0.40
    sements
    0.38
     sle
    0.38
     slimming
    0.38
     personalization
    0.37
     sml
    0.36
     lash
    0.35
     sass
    0.34
    藉
    0.34
    cism
    0.34
    Activations Density 0.000%

    No Known Activations