© 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. 4-CLT-HP
    7. 479
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    DockStyle
    -0.70
    Geplaatst
    -0.69
    ImageContext
    -0.69
    ędzynarod
    -0.63
    StoryboardSegue
    -0.60
    cayaan
    -0.60
    SharedDtor
    -0.59
    ogaster
    -0.59
    autique
    -0.58
    onAttach
    -0.58
    POSITIVE LOGITS
    原始内容存档于
    0.58
    __':
    0.52
     their
    0.50
    their
    0.50
    SuspendLayout
    0.48
    Their
    0.48
     deres
    0.47
     EdgeInsets
    0.46
     Their
    0.46
    WEBPACK
    0.44
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.