© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 1-CLT-HP
    7. 13592
    Prev
    Next
    INDEX
    Explanations

    shoulder

    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
     shoulder
    -1.38
     Shoulder
    -1.37
    shoulder
    -1.33
    Shoulder
    -1.18
     shoulders
    -0.90
     Shoulders
    -0.79
    Gambas
    -0.73
     Schulter
    -0.71
     hombro
    -0.67
    ULDER
    -0.67
    POSITIVE LOGITS
    发表于
    0.57
    yntaxException
    0.56
    WebpackPlugin
    0.54
    +#+#
    0.53
    PasswordEncoder
    0.49
     ComVisible
    0.49
     onlyOwner
    0.46
    revision
    0.46
    typeorm
    0.45
     Núñez
    0.45
    Activations Density 0.003%

    No Known Activations