© 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. 5-CLT-HP
    7. 92251
    Prev
    Next
    INDEX
    Explanations

    braking

    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
    bootstrapcdn
    -0.76
     ujednoznacz
    -0.73
     AssemblyCulture
    -0.71
     EconPapers
    -0.61
    sizeCache
    -0.60
    StoreMessageInfo
    -0.58
     Tha
    -0.54
     Penh
    -0.53
    setVerticalGroup
    -0.53
    Tha
    -0.53
    POSITIVE LOGITS
    roblast
    0.47
    ">//
    0.46
    ParallelGroup
    0.45
    原始内容存档于
    0.45
    cession
    0.45
    /**
    0.40
    romptu
    0.40
    épreuve
    0.40
    """
    0.40
    ness
    0.40
    Activations Density 0.001%

    No Known Activations