© 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. 95148
    Prev
    Next
    INDEX
    Explanations

    systemic

    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
    i
    -0.82
     $_"
    -0.75
    e
    -0.75
     himſelf
    -0.75
     zelve
    -0.75
     Majefty
    -0.74
     bishop
    -0.73
     myſelf
    -0.73
     themſelves
    -0.72
    ed
    -0.71
    POSITIVE LOGITS
    aarrggbb
    0.51
     EClass
    0.47
     pu
    0.46
    /******/
    0.45
     Art
    0.44
    ueil
    0.44
     art
    0.43
     Weh
    0.42
     ek
    0.42
     real
    0.42
    Activations Density 0.064%

    No Known Activations