© 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. 0-CLT-HP
    7. 44094
    Prev
    Next
    INDEX
    Explanations

    (in)consistency

    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
    consistent
    -1.59
     consistent
    -1.59
     Consistent
    -1.51
    Consistent
    -1.51
     Consistency
    -1.38
     inconsistent
    -1.34
    consistency
    -1.28
     consistency
    -1.27
    Consistency
    -1.26
     uniformly
    -1.20
    POSITIVE LOGITS
    ly
    0.49
     dit
    0.48
    ness
    0.47
     daily
    0.47
    inte
    0.45
    ❝
    0.45
     te
    0.44
     street
    0.44
     dá
    0.44
     non
    0.43
    Activations Density 0.079%

    No Known Activations