© 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. 1-CLT-HP
    7. 13621
    Prev
    Next
    INDEX
    Explanations

    programming code

    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
    bsen
    -2.14
    Tembelea
    -0.73
    Vidite
    -0.71
    WriteBarrier
    -0.66
     Walkover
    -0.65
    GEBURTSDATUM
    -0.61
     EconPapers
    -0.60
     AppCompatTheme
    -0.60
    الحياه
    -0.60
    RepeatedField
    -0.59
    POSITIVE LOGITS
     OGSÅ
    0.48
    oltán
    0.46
     Til
    0.46
    囲
    0.46
    かれています
    0.45
     import
    0.45
    évaluateur
    0.44
    liosis
    0.44
    __":
    0.44
    noop
    0.44
    Activations Density 0.006%

    No Known Activations