© 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. 97012
    Prev
    Next
    INDEX
    Explanations

    button

    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
     متعلقه
    -0.88
    pushFollow
    -0.66
    enumi
    -0.64
    andExpect
    -0.64
     مشين
    -0.62
     button
    -0.61
     "..\..\
    -0.61
    TestBed
    -0.61
     "..\..\..\
    -0.61
    atguigu
    -0.61
    POSITIVE LOGITS
    <bos>
    0.66
    مصادر
    0.63
     address
    0.47
     held
    0.46
     present
    0.43
     pair
    0.42
    ęku
    0.42
    ↵↵
    0.41
     performed
    0.41
    VideoCapture
    0.40
    Activations Density 0.536%

    No Known Activations