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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 90565
    Prev
    Next
    INDEX
    Explanations

    science and technology

    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
     Mig
    -0.60
    Mig
    -0.51
     Mic
    -0.50
     d
    -0.48
     I
    -0.46
    RenderAtEndOf
    -0.46
     Paglinawan
    -0.45
     Turn
    -0.45
    Immortal
    -0.44
    Mic
    -0.43
    POSITIVE LOGITS
     Efq
    0.98
    ^(@)
    0.89
     pleaſure
    0.85
     Monfieur
    0.84
     Theſe
    0.83
     themſelves
    0.83
     himſelf
    0.82
    ſelf
    0.82
     poffible
    0.82
    i
    0.82
    Activations Density 0.043%

    No Known Activations