© 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. 97300
    Prev
    Next
    INDEX
    Explanations

    comfort, isolation

    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
    ModelSerializer
    -0.63
    hetamine
    -0.59
    AllAfrica
    -0.58
     exports
    -0.57
     ports
    -0.56
     "":
    -0.56
     submarines
    -0.55
     Studenten
    -0.55
    spreis
    -0.55
    ={({
    -0.55
    POSITIVE LOGITS
    :✨
    0.56
     distanciation
    0.56
    BeginInit
    0.50
     Réponses
    0.49
     nini
    0.47
    OCCURRED
    0.46
    BeginContext
    0.46
     متعلقه
    0.46
     allá
    0.44
    CodedInputStream
    0.44
    Activations Density 0.019%

    No Known Activations