© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 94884
    Prev
    Next
    INDEX
    Explanations

    computer code/internet content

    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
    äsident
    -0.65
    NOPQRST
    -0.63
    tagHelperRunner
    -0.63
    KURZBESCHREIBUNG
    -0.60
    TagMode
    -0.58
     typelib
    -0.58
    IntoConstraints
    -0.58
     beginnetje
    -0.58
    themselves
    -0.57
    Архівовано
    -0.57
    POSITIVE LOGITS
    setObjectName
    0.46
    ài
    0.44
     obtient
    0.43
    addPreferredGap
    0.42
    Wanted
    0.42
    addGap
    0.41
    isNotBlank
    0.41
     Norvège
    0.41
    {'
    0.40
     linkovi
    0.40
    Activations Density 0.015%

    No Known Activations