© 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. 1-CLT-HP
    7. 12460
    Prev
    Next
    INDEX
    Explanations

    lighthouse

    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
     lighthouse
    -1.06
     Lighthouse
    -0.88
    ligh
    -0.69
    CPtr
    -0.55
    IDA
    -0.51
     ligh
    -0.48
    Duc
    -0.47
    effetto
    -0.46
     Fost
    -0.46
    n
    -0.45
    POSITIVE LOGITS
    SequentialGroup
    1.10
     pinulongan
    0.82
    IBOutlet
    0.68
    uxxxx
    0.68
    extAlignment
    0.64
     CreateTagHelper
    0.64
    antMatchers
    0.63
    mphony
    0.63
    __":
    0.62
    apunov
    0.61
    Activations Density 0.108%

    No Known Activations