© 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. 1-CLT-HP
    4. 272
    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
    -0.91
     in
    -0.76
     –
    -0.75
    and
    -0.68
     at
    -0.66
     with
    -0.65
     for
    -0.65
     of
    -0.64
     on
    -0.64
     from
    -0.62
    POSITIVE LOGITS
     définiti
    0.95
    WebVitals
    0.90
    MLLoader
    0.90
     fermés
    0.88
     varandra
    0.85
     vectorielles
    0.85
     stället
    0.85
    DockStyle
    0.83
    PreferredItem
    0.82
    +#+#
    0.82
    Activations Density 0.044%

    No Known Activations