© 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
    2. Gemma-2-2B
    3. 0-CLT-HP
    4. 40455
    Prev
    Next
    INDEX
    Explanations

    bore

    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
    bore
    -1.20
    Datuak
    -0.83
    PreferredItem
    -0.74
     AssemblyTitle
    -0.73
    setVerticalGroup
    -0.72
    tvguidetime
    -0.72
    CppMethod
    -0.70
    anmoins
    -0.70
     doInBackground
    -0.69
    webElementXpaths
    -0.68
    POSITIVE LOGITS
    EventData
    0.48
    ristan
    0.43
     الاطلاع
    0.42
    WHM
    0.42
     et
    0.41
    rotto
    0.40
     I
    0.40
     origin
    0.40
    <eos>
    0.40
     prie
    0.40
    Activations Density 1.130%

    No Known Activations