© 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. 96191
    Prev
    Next
    INDEX
    Explanations

    1

    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
    LookAnd
    -0.96
    TypedDataSet
    -0.77
     betweenstory
    -0.77
     propOrder
    -0.75
    webElementXpaths
    -0.69
    ActionCreators
    -0.68
    ]]
    -0.66
     Numerade
    -0.65
    SceneManagement
    -0.65
    IntoConstraints
    -0.65
    POSITIVE LOGITS
     Corée
    0.44
    Poland
    0.40
     seguinte
    0.40
     %=
    0.40
     Guinée
    0.39
    utilisons
    0.38
     Irán
    0.38
    lidays
    0.38
    Alberta
    0.38
     güne
    0.38
    Activations Density 0.000%

    No Known Activations