© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 41838
    Prev
    Next
    INDEX
    Explanations

    Pak

    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
     autorytatywna
    -0.85
     invokingState
    -0.67
    )}</
    -0.66
    IUrlHelper
    -0.65
    findpost
    -0.63
    rrggbb
    -0.60
    PRWEB
    -0.60
     accommodating
    -0.60
    ()]);
    -0.59
    "});
    -0.58
    POSITIVE LOGITS
    tion
    0.52
    ning
    0.49
     menyus
    0.45
    angi
    0.45
    ening
    0.44
    ation
    0.43
    ization
    0.43
     Laid
    0.42
     maintien
    0.42
    laid
    0.42
    Activations Density 0.555%

    No Known Activations