© 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. 1-CLT-HP
    7. 15870
    Prev
    Next
    INDEX
    Explanations

    building up something

    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
    AddTagHelper
    -1.09
    awtextra
    -0.95
    InjectAttribute
    -0.78
    ChildScrollView
    -0.69
    WriteTagHelper
    -0.67
    DockStyle
    -0.66
    AndEndTag
    -0.65
    HasForeignKey
    -0.65
     CreateTagHelper
    -0.64
    FormTagHelper
    -0.64
    POSITIVE LOGITS
    dbh
    0.50
    ciąg
    0.49
    vel
    0.46
    形
    0.46
     AutoMapper
    0.45
    brechen
    0.44
     getHeight
    0.44
    dshaw
    0.44
     rythme
    0.42
    bble
    0.42
    Activations Density 0.036%

    No Known Activations