© 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. 0-CLT-HP
    7. 41553
    Prev
    Next
    INDEX
    Explanations

    illary

    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
    illary
    -1.14
    erez
    -0.93
     strada
    -0.47
     hes
    -0.46
    ecuzione
    -0.46
    getExternal
    -0.46
    Desire
    -0.45
    o
    -0.45
     cromado
    -0.45
     externo
    -0.44
    POSITIVE LOGITS
    SourceChecksum
    0.96
     мәкалә
    0.80
    Tikang
    0.78
    enumi
    0.77
    DockStyle
    0.75
    RenderAtEndOf
    0.75
    IsMutable
    0.75
    IUrlHelper
    0.73
    <bos>
    0.72
    protoimpl
    0.71
    Activations Density 1.581%

    No Known Activations