© 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. 40019
    Prev
    Next
    INDEX
    Explanations

    politics and government

    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
    saraba
    -0.75
     تضيفلها
    -0.75
    UrlResolution
    -0.71
    postIndex
    -0.68
    +#+
    -0.65
     Chwiliwch
    -0.61
    ########.
    -0.60
     courting
    -0.60
     utafitiHapana
    -0.60
     reformation
    -0.59
    POSITIVE LOGITS
    s
    0.68
    ly
    0.58
    sing
    0.47
    RICAL
    0.46
    ся
    0.45
     henvisninger
    0.44
     приго
    0.43
     continuant
    0.43
    :@"
    0.43
    ckså
    0.42
    Activations Density 0.196%

    No Known Activations