© 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. 43122
    Prev
    Next
    INDEX
    Explanations

    revolution

    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
     revolution
    -1.84
    revolution
    -1.76
     Revolution
    -1.70
    Revolution
    -1.66
     REVOLUTION
    -1.59
     révolution
    -1.53
    revolutionary
    -1.45
     revolutionary
    -1.41
     revolu
    -1.34
    Revolutionary
    -1.23
    POSITIVE LOGITS
    s
    0.61
    raires
    0.51
    n
    0.51
    ist
    0.47
    alleye
    0.45
    d
    0.45
    ry
    0.44
    ists
    0.43
    ski
    0.43
    ary
    0.42
    Activations Density 0.047%

    No Known Activations