© 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. 5-CLT-HP
    7. 5806
    Prev
    Next
    INDEX
    Explanations

    work

    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
     kasarigan
    -0.54
     >=",
    -0.54
    ed
    -0.51
    фо
    -0.48
    que
    -0.47
    ţa
    -0.47
    foreground
    -0.43
    ved
    -0.43
    ab
    -0.42
    ischer
    -0.42
    POSITIVE LOGITS
     فريبيس
    0.96
    ^(@)
    0.81
     purpoſe
    0.75
     pleaſure
    0.71
     auroit
    0.68
     leſs
    0.66
    findpost
    0.65
     étoit
    0.65
     leaſt
    0.65
     ſeveral
    0.65
    Activations Density 0.015%

    No Known Activations