© 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. 2509
    Prev
    Next
    INDEX
    Explanations

    and

    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
    #+#
    -0.63
    ParallelGroup
    -0.60
    aspectj
    -0.59
    ppuden
    -0.58
    rungsseite
    -0.57
    GenerationType
    -0.55
    AILS
    -0.54
    Filmographie
    -0.54
    xymatrix
    -0.54
    서는
    -0.52
    POSITIVE LOGITS
    хьтан
    0.59
     moindre
    0.49
    findpost
    0.47
     dedans
    0.46
     this
    0.45
    kuuta
    0.45
     it
    0.45
    racene
    0.43
    calipsis
    0.43
     ExecuteAsync
    0.43
    Activations Density 0.005%

    No Known Activations