© 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. 4416
    Prev
    Next
    INDEX
    Explanations

    became

    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
    GEBURTSDATUM
    -1.05
    ConstraintMaker
    -0.99
     EconPapers
    -0.95
    yship
    -0.86
     ExecuteAsync
    -0.85
     Theſe
    -0.85
    ✨:
    -0.85
     initComponents
    -0.83
    noons
    -0.83
    NUMX
    -0.83
    POSITIVE LOGITS
    ).
    0.45
    )
    0.40
     (
    0.40
    )).
    0.37
     couvert
    0.37
     OTHERWISE
    0.37
     otherwise
    0.36
    our
    0.36
     )
    0.35
    –
    0.35
    Activations Density 0.291%

    No Known Activations