© 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. 4-CLT-HP
    7. 2796
    Prev
    Next
    INDEX
    Explanations

    edges and boundaries

    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
    UrlResolution
    -0.74
    ArrowToggle
    -0.71
    دانشنامهٔ
    -0.65
    GIVEREF
    -0.62
     invokingState
    -0.61
     Roskov
    -0.60
    <bos>
    -0.59
     SwitchCompat
    -0.59
    AsUp
    -0.57
     mineures
    -0.57
    POSITIVE LOGITS
     BoxDecoration
    0.51
    ChildScrollView
    0.50
    ধ্য
    0.43
     jScrollPane
    0.43
    PMailer
    0.42
    makeConstraints
    0.41
    gatsby
    0.40
     passim
    0.39
    amssymb
    0.39
     proposed
    0.39
    Activations Density 0.006%

    No Known Activations