© 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. 71973
    Prev
    Next
    INDEX
    Explanations

    there

    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
     there
    -1.98
    there
    -1.69
     THERE
    -1.61
     There
    -1.52
    There
    -1.52
    THERE
    -1.42
     thither
    -1.13
    theres
    -1.04
    πάρχ
    -1.02
     acolo
    -0.98
    POSITIVE LOGITS
     are
    0.42
     mon
    0.39
     én
    0.39
     en
    0.37
     can
    0.37
     Gav
    0.37
     ple
    0.36
     %}
    0.36
    "]));
    0.35
    Edm
    0.35
    Activations Density 0.008%

    No Known Activations