© 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. 93879
    Prev
    Next
    INDEX
    Explanations

    organizations and measuring

    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
     measuring
    -0.78
    measuring
    -0.63
     Measuring
    -0.60
    Measuring
    -0.57
    ContentAsync
    -0.52
    omycin
    -0.51
     Measurements
    -0.48
    ensas
    -0.48
    ftagPool
    -0.48
    measured
    -0.47
    POSITIVE LOGITS
     ſche
    0.68
    المناصب
    0.65
    BufferException
    0.64
    saraba
    0.63
     Jefus
    0.60
     Conſ
    0.58
     greateſt
    0.58
     ſta
    0.57
    mphony
    0.56
    ſelf
    0.56
    Activations Density 1.394%

    No Known Activations