© 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. 1-CLT-HP
    7. 11552
    Prev
    Next
    INDEX
    Explanations

    Heat/heating

    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
    ⓘ
    -0.65
    kür
    -0.60
    ésultat
    -0.60
    gründ
    -0.52
     sécher
    -0.51
    contentLoaded
    -0.50
     oprot
    -0.49
    rmtree
    -0.49
    NOPQRST
    -0.48
    écuter
    -0.48
    POSITIVE LOGITS
     island
    0.61
    island
    0.59
    endphp
    0.53
    Island
    0.50
     ilha
    0.50
    URLEncoder
    0.50
    devamını
    0.48
    MethodManager
    0.48
    CastException
    0.47
     islands
    0.47
    Activations Density 0.016%

    No Known Activations