© 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. 20-CLT-HP
    7. 76423
    Prev
    Next
    INDEX
    Explanations

    r

    np_max-act-logits · 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
     تضيفلها
    -0.82
     дописавши
    -0.79
    RenderAtEndOf
    -0.79
     تانيه
    -0.75
    zerland
    -0.75
    awtextra
    -0.75
     '{@
    -0.73
    paksa
    -0.73
    DockStyle
    -0.72
     surla
    -0.71
    POSITIVE LOGITS
    uts
    0.59
    UTS
    0.44
    te
    0.42
    id
    0.41
    akes
    0.40
    antMatchers
    0.38
    Vac
    0.38
    tek
    0.38
    penuhi
    0.37
     vallée
    0.36
    Activations Density 0.001%

    No Known Activations