© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-CLT-HP
    7. 2070
    Prev
    Next
    INDEX
    Explanations

    HTML

    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
     onOptions
    -0.71
     MaterialApp
    -0.56
    hoeddwyd
    -0.55
    peño
    -0.54
    StructEnd
    -0.53
     odkazy
    -0.52
     Hinata
    -0.52
     Biblia
    -0.51
    empty
    -0.49
    Handles
    -0.49
    POSITIVE LOGITS
     both
    0.58
    ,
    0.52
    WriteBarrier
    0.52
    erman
    0.51
    __',
    0.51
    enterOuterAlt
    0.50
    unanje
    0.50
    ▼
    0.48
     super
    0.48
    ![
    0.48
    Activations Density 0.021%

    No Known Activations