© 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. 4-CLT-HP
    7. 1508
    Prev
    Next
    INDEX
    Explanations

    general sentences

    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
    awaiter
    -0.73
    GeneratedCode
    -0.70
     HasFactory
    -0.65
     AssemblyVersion
    -0.62
     newBuilder
    -0.62
    
    -0.61
    ArgsConstructor
    -0.61
    windowFixed
    -0.61
     cherchés
    -0.59
    NamedQueries
    -0.59
    POSITIVE LOGITS
     song
    0.63
     interviews
    0.58
     songs
    0.58
     hymn
    0.52
    õi
    0.51
     Sheik
    0.50
     psalm
    0.48
    cdef
    0.48
     hymns
    0.48
    enumi
    0.47
    Activations Density 0.001%

    No Known Activations