© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 41304
    Prev
    Next
    INDEX
    Explanations

    tortoise

    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
    s
    -0.99
    tling
    -0.91
    ی
    -0.91
    ième
    -0.82
    soever
    -0.78
    ergies
    -0.78
    InputBorder
    -0.76
    t
    -0.76
    er
    -0.75
    RenderAtEndOf
    -0.73
    POSITIVE LOGITS
     dig
    0.60
     go
    0.50
     information
    0.50
     models
    0.50
     Gra
    0.50
    '
    0.49
    uger
    0.48
     forward
    0.48
     pro
    0.48
    ’
    0.47
    Activations Density 0.088%

    No Known Activations