© 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. 77497
    Prev
    Next
    INDEX
    Explanations

    variations of "out"

    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
     removal
    -0.82
     removing
    -0.73
     removed
    -0.71
    removal
    -0.69
     REMOV
    -0.63
     removes
    -0.62
     remove
    -0.61
     removals
    -0.61
     Removal
    -0.61
    removing
    -0.59
    POSITIVE LOGITS
     out
    1.16
     Out
    0.98
    Out
    0.93
    out
    0.88
     OUT
    0.84
     Normdatei
    0.67
    outs
    0.66
    getOut
    0.66
     away
    0.66
    OUT
    0.65
    Activations Density 0.000%

    No Known Activations