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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 45141
    Prev
    Next
    INDEX
    Explanations

    demarcation

    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
     predecessor
    -0.52
     transfé
    -0.51
     sobě
    -0.50
     Waray
    -0.49
     counterpart
    -0.49
     mourir
    -0.49
     legacies
    -0.49
    suck
    -0.49
    ceğine
    -0.48
     demarcation
    -0.48
    POSITIVE LOGITS
    liminaries
    0.68
     AssemblyCulture
    0.65
    ed
    0.60
    idable
    0.59
    iming
    0.57
    +#+#
    0.55
    ił
    0.54
    iendo
    0.54
    hemiah
    0.53
    ه
    0.53
    Activations Density 0.225%

    No Known Activations