© 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. 4-CLT-HP
    7. 924
    Prev
    Next
    INDEX
    Explanations

    footnotes

    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
     Therm
    -0.40
     Penta
    -0.40
     Thermo
    -0.39
    それと
    -0.36
    Penta
    -0.36
     BaseController
    -0.35
    Př
    -0.35
    kháu
    -0.35
    embre
    -0.35
    起
    -0.34
    POSITIVE LOGITS
    ſelf
    0.91
    "]];
    0.88
     houſe
    0.86
    "]);
    0.86
     Monfieur
    0.85
     Houſe
    0.84
    '},
    0.84
    "):
    0.84
     Chriftian
    0.82
     Efq
    0.82
    Activations Density 0.022%

    No Known Activations