© 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. 20-CLT-HP
    7. 75815
    Prev
    Next
    INDEX
    Explanations

    Introductions or technical documentation

    np_max-act-logits · 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
    featureID
    -0.65
    WriteTagHelper
    -0.62
     שוליים
    -0.57
     Abschied
    -0.56
     skj
    -0.55
     nhàng
    -0.53
    SearchResult
    -0.53
    abcdefghijklmnop
    -0.52
     помощь
    -0.52
    AndEndTag
    -0.52
    POSITIVE LOGITS
     near
    0.74
    HasAnnotation
    0.60
    near
    0.57
    
    0.54
    DockStyle
    0.50
     surla
    0.50
    Near
    0.50
    awtextra
    0.50
     AssemblyTitle
    0.48
    #+#
    0.47
    Activations Density 0.000%

    No Known Activations