© 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. 1-CLT-HP
    7. 10012
    Prev
    Next
    INDEX
    Explanations

    oo

    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
    oo
    -1.86
    OO
    -1.41
    ooo
    -1.25
    oooo
    -1.07
    oooooo
    -0.95
    ooooooo
    -0.93
    OOO
    -0.91
    ooh
    -0.91
    oooooooo
    -0.87
    oob
    -0.84
    POSITIVE LOGITS
    a
    0.93
    i
    0.82
    e
    0.82
    PHeader
    0.69
    ftagPool
    0.68
     насељу
    0.68
    Personendaten
    0.65
    Obrázky
    0.65
    ^(@)
    0.65
     EconPapers
    0.65
    Activations Density 0.029%

    No Known Activations