© 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. 5-CLT-HP
    7. 92480
    Prev
    Next
    INDEX
    Explanations

    quantifiers

    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
    FailureListener
    -0.65
    InputBorder
    -0.58
    ChildScrollView
    -0.58
    PasswordEncoder
    -0.58
    sizeCache
    -0.56
    expandindo
    -0.55
     محفوظة
    -0.54
     surla
    -0.54
    Slf
    -0.54
    reactivex
    -0.54
    POSITIVE LOGITS
    ۪
    0.58
    .")
    0.51
    ghts
    0.50
    dije
    0.50
     juſ
    0.49
     hiér
    0.49
    tidaknya
    0.48
     ſome
    0.48
     estekak
    0.47
    appi
    0.47
    Activations Density 0.032%

    No Known Activations