© 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. 4-CLT-HP
    4. 3524
    Prev
    Next
    INDEX
    Explanations

    ,

    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
     and
    -0.94
     Because
    -0.73
     However
    -0.73
     Then
    -0.71
     But
    -0.71
    and
    -0.71
     They
    -0.70
     Maybe
    -0.68
     Perhaps
    -0.68
     Finally
    -0.68
    POSITIVE LOGITS
     negroes
    0.62
    venirs
    0.61
     Cæsar
    0.58
    VersionUID
    0.57
     Perseus
    0.57
    runApp
    0.56
     myſelf
    0.56
     ninjas
    0.55
     neutrality
    0.54
    UpInside
    0.54
    Activations Density 0.001%

    No Known Activations