© 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
    2. Gemma-2-2B
    3. 5-CLT-HP
    4. 92886
    Prev
    Next
    INDEX
    Explanations

    hyphen

    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
     ModelRenderer
    -0.56
    )");
    
    -0.52
     ainfi
    -0.51
     Efq
    -0.51
    ERÍA
    -0.48
     daihatsu
    -0.47
    )"),
    -0.47
     $_"
    -0.46
     дописавши
    -0.46
    vény
    -0.46
    POSITIVE LOGITS
    -
    0.95
    0
    0.82
    2
    0.79
    5
    0.73
    1
    0.73
    3
    0.72
    6
    0.72
    8
    0.71
    4
    0.70
    InjectAttribute
    0.68
    Activations Density 0.002%

    No Known Activations