© 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. 4-CLT-HP
    7. 3327
    Prev
    Next
    INDEX
    Explanations

    copyright

    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
    SourceChecksum
    -0.54
    mstyle
    -0.50
    Geplaatst
    -0.48
    InstrumentedTest
    -0.47
     inapropiados
    -0.46
    InjectAttribute
    -0.46
    opsida
    -0.46
    omials
    -0.46
     Ush
    -0.45
    PropertyChanging
    -0.42
    POSITIVE LOGITS
    DOCTYPE
    0.60
     more
    0.60
     sepenuhnya
    0.56
    esz
    0.55
     页
    0.55
     solely
    0.54
    '));
    0.54
     entirely
    0.54
    #+#
    0.54
     neighbor
    0.52
    Activations Density 0.004%

    No Known Activations