© 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. 96223
    Prev
    Next
    INDEX
    Explanations

    African countries

    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
    tanleria
    -0.67
    Roman
    -0.60
     endwhile
    -0.60
    photobucket
    -0.57
    Raj
    -0.53
     holographic
    -0.53
    Jord
    -0.52
     IP
    -0.52
    jarige
    -0.51
    Romans
    -0.51
    POSITIVE LOGITS
     Guinea
    0.61
     guinea
    0.53
     ComVisible
    0.48
     AssemblyCulture
    0.46
    InteropServices
    0.45
    PYX
    0.45
    Guinea
    0.44
     Ngb
    0.44
    GUN
    0.43
    HasBeenSet
    0.43
    Activations Density 0.004%

    No Known Activations