© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-CLT-HP
    7. 2408
    Prev
    Next
    INDEX
    Explanations

    unknown information

    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
    ADOS
    -0.46
    ados
    -0.44
    outs
    -0.43
     te
    -0.43
    iffs
    -0.43
     Martens
    -0.42
    emo
    -0.41
     ar
    -0.40
    HEA
    -0.40
     los
    -0.39
    POSITIVE LOGITS
    ViewFeatures
    0.79
     autorytatywna
    0.75
     gynhyrchwyd
    0.73
     AssemblyTitle
    0.69
    UseVisualStyle
    0.69
    LookAnd
    0.67
    ondissement
    0.67
     AssemblyCompany
    0.65
    AntiForgeryToken
    0.65
    $")
    0.64
    Activations Density 0.008%

    No Known Activations