© 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. 81
    Prev
    Next
    INDEX
    Explanations

    Punctuation

    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
     order
    -0.46
     option
    -0.45
     one
    -0.45
     nau
    -0.44
    Expedia
    -0.43
    order
    -0.42
    classnames
    -0.42
     long
    -0.41
    ————————————————
    -0.41
     OPTION
    -0.40
    POSITIVE LOGITS
    رشف
    0.69
    PreInfinity
    0.67
    ConstraintMaker
    0.65
    #+#
    0.65
     chopsticks
    0.64
    tvguidetime
    0.61
    seamnă
    0.61
    клопе
    0.60
    iprot
    0.60
     Audiodateien
    0.59
    Activations Density 0.002%

    No Known Activations