© 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. 74755
    Prev
    Next
    INDEX
    Explanations

    computer code

    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
    ResumeLayout
    -0.71
     مشين
    -0.61
    httphttps
    -0.59
    "](
    -0.56
    RRect
    -0.51
    Jereo
    -0.50
    .«
    -0.50
    ArgsConstructor
    -0.49
     Sachen
    -0.48
    Tikang
    -0.47
    POSITIVE LOGITS
    gemeester
    0.50
    odymium
    0.47
    ├──
    0.47
     nakalista
    0.46
    acağına
    0.46
    Powder
    0.45
    mandu
    0.45
    iets
    0.44
    MeV
    0.43
    OptionsMenu
    0.43
    Activations Density 0.005%

    No Known Activations