© 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. 5-CLT-HP
    7. 93051
    Prev
    Next
    INDEX
    Explanations

    to

    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
     pleaf
    -0.82
     ſeveral
    -0.68
     occaf
    -0.67
     poffible
    -0.66
     purpoſe
    -0.66
     Jefus
    -0.64
     feveral
    -0.63
     myſelf
    -0.63
     Theſe
    -0.62
     pleaſure
    -0.62
    POSITIVE LOGITS
     try
    0.88
     keep
    0.80
     preserve
    0.77
     get
    0.71
     save
    0.69
     make
    0.67
     maintain
    0.65
     protect
    0.62
     establish
    0.62
     ensure
    0.62
    Activations Density 0.002%

    No Known Activations