© 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. 0-CLT-HP
    7. 92465
    Prev
    Next
    INDEX
    Explanations

    scientific/technical analysis

    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
     packed
    -0.77
     AssemblyTitle
    -0.73
     packing
    -0.66
    SourceChecksum
    -0.63
    évaluateur
    -0.59
    featureID
    -0.58
    StreetMap
    -0.56
     ExecuteAsync
    -0.54
    رشف
    -0.54
    ViewFeatures
    -0.54
    POSITIVE LOGITS
    
    0.65
    andExpect
    0.63
    temberg
    0.61
    netbeans
    0.61
    Filmografie
    0.59
    φαλ
    0.58
    Temporary
    0.54
    mpf
    0.54
    IGATION
    0.54
    loro
    0.53
    Activations Density 0.060%

    No Known Activations