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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 96048
    Prev
    Next
    INDEX
    Explanations

    suffixes and prepositions

    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
     demos
    -0.51
    áře
    -0.49
    edos
    -0.45
     bands
    -0.45
     gaps
    -0.44
    campista
    -0.44
    edoc
    -0.44
     primers
    -0.43
    imread
    -0.43
     hospitals
    -0.43
    POSITIVE LOGITS
     CreateTagHelper
    0.84
    RenderAtEndOf
    0.77
     AssemblyCulture
    0.76
     nahilalakip
    0.74
    SourceChecksum
    0.73
    новниш
    0.71
    URLException
    0.68
    PropertyChanging
    0.66
     Administrativna
    0.66
    ValueStyle
    0.65
    Activations Density 0.013%

    No Known Activations