© 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. 95022
    Prev
    Next
    INDEX
    Explanations

    requests, changes, offers

    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
     للمعارف
    -0.81
     متعلقه
    -0.80
     Normdatei
    -0.78
    IsContent
    -0.77
     utafitiHapana
    -0.77
     itſelf
    -0.76
    poptosis
    -0.75
     myſelf
    -0.74
    aneous
    -0.73
     mohair
    -0.71
    POSITIVE LOGITS
     the
    1.13
     a
    1.03
     an
    0.79
     it
    0.76
     their
    0.76
     its
    0.75
     this
    0.71
     these
    0.69
     them
    0.67
     some
    0.66
    Activations Density 0.065%

    No Known Activations