© 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. 94422
    Prev
    Next
    INDEX
    Explanations

    technical/work contexts

    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
    +#+#
    -0.93
     فريبيس
    -0.82
    IUrlHelper
    -0.78
     moschino
    -0.75
     Cæsar
    -0.73
    󠁧
    -0.71
     myſelf
    -0.70
     holotype
    -0.69
     IAEA
    -0.69
     ―――――
    -0.69
    POSITIVE LOGITS
    ers
    0.60
     a
    0.59
     ur
    0.52
     the
    0.52
     any
    0.52
    ism
    0.49
    psin
    0.49
    ing
    0.45
    ēs
    0.45
     age
    0.44
    Activations Density 1.539%

    No Known Activations