© 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. 5389
    Prev
    Next
    INDEX
    Explanations

    web paths and URLs

    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
    parsedMessage
    -0.87
    IntoConstraints
    -0.84
    UnsafeEnabled
    -0.82
     NSCoder
    -0.73
     MainAxisSize
    -0.73
    StoryboardSegue
    -0.73
    ModelSerializer
    -0.68
    CppMethod
    -0.68
    AnchorStyles
    -0.68
    ChildScrollView
    -0.66
    POSITIVE LOGITS
    #
    0.53
    <sub>
    0.51
    1
    0.49
    model
    0.48
    data
    0.47
    [
    0.47
    Real
    0.46
     #
    0.45
    (
    0.45
    _
    0.44
    Activations Density 0.057%

    No Known Activations