© 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
    2. Gemma-2-2B
    3. 0-CLT-HP
    4. 39942
    Prev
    Next
    INDEX
    Explanations

    manner

    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
     manner
    -1.58
    manner
    -1.48
     '\\;'
    -1.24
     subjects
    -1.07
    abestanden
    -1.07
    subjects
    -1.05
    MigrationBuilder
    -1.05
     AssemblyCulture
    -1.02
    expandindo
    -1.02
     Manner
    -1.01
    POSITIVE LOGITS
     for
    0.51
     with
    0.51
     of
    0.51
     who
    0.51
     where
    0.46
    лист
    0.45
    ed
    0.43
    gning
    0.43
    くると
    0.41
     lleve
    0.41
    Activations Density 1.176%

    No Known Activations