© 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
    2. Gemma-2-2B
    3. 0-CLT-HP
    4. 45648
    Prev
    Next
    INDEX
    Explanations

    water/air waves

    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
    ########.
    -1.02
     ſtate
    -0.92
     purpoſe
    -0.90
     ſche
    -0.88
     Majefty
    -0.84
    ſelf
    -0.79
     fubject
    -0.78
     houſe
    -0.76
     pleaſure
    -0.75
    ſelves
    -0.73
    POSITIVE LOGITS
     am
    0.48
     contributo
    0.47
     contributing
    0.46
     bidra
    0.46
    coloured
    0.45
    greja
    0.45
     landed
    0.44
     komt
    0.44
    isContained
    0.44
    Continues
    0.44
    Activations Density 0.110%

    No Known Activations