© 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. 43025
    Prev
    Next
    INDEX
    Explanations

    PRP

    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
    y
    -0.72
     تانيه
    -0.67
    er
    -0.60
    erate
    -0.59
    yla
    -0.57
     disponibilités
    -0.57
     Stork
    -0.56
    bakar
    -0.56
     مرئيه
    -0.55
    yyy
    -0.54
    POSITIVE LOGITS
     <=",
    0.63
    IsContent
    0.55
    ölcs
    0.52
    ervlak
    0.50
    ValueStyle
    0.49
    thien
    0.49
    Бахар
    0.48
    ✭✭
    0.48
    Brainz
    0.46
    ̍t
    0.45
    Activations Density 1.320%

    No Known Activations