© 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. 4-CLT-HP
    7. 4962
    Prev
    Next
    INDEX
    Explanations

    lab/classroom settings

    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
     виправивши
    -0.53
     насељу
    -0.53
     CURIAM
    -0.51
     елның
    -0.51
     solaire
    -0.51
     apnea
    -0.51
    Rüyada
    -0.50
     disambiguazione
    -0.50
    flat
    -0.49
     murale
    -0.49
    POSITIVE LOGITS
     dominated
    0.64
     Nation
    0.63
     nationwide
    0.61
    tvguidetime
    0.60
     populated
    0.60
     around
    0.59
     nation
    0.59
     across
    0.59
     staffed
    0.57
     everywhere
    0.56
    Activations Density 0.002%

    No Known Activations