© 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. 5-CLT-HP
    7. 94642
    Prev
    Next
    INDEX
    Explanations

    processes, movement, connectivity

    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
    ativement
    -0.66
     revanche
    -0.65
     nakalista
    -0.64
     axons
    -0.61
    تفصیلات
    -0.59
    انه
    -0.58
     كومونز
    -0.57
    ፩
    -0.57
    ographs
    -0.57
    Branches
    -0.57
    POSITIVE LOGITS
     occurred
    0.60
     occur
    0.59
     occurring
    0.56
     виправивши
    0.54
     ocur
    0.54
     happening
    0.52
     here
    0.50
     inplace
    0.50
     happened
    0.50
     happen
    0.49
    Activations Density 0.012%

    No Known Activations