© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 1-CLT-HP
    7. 16230
    Prev
    Next
    INDEX
    Explanations

    "ine" suffix

    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
    Negative Logits
     surla
    -0.56
    Nazionale
    -0.55
    ExecuteReader
    -0.54
    AxisAlignment
    -0.49
    Menge
    -0.48
    irent
    -0.48
     architecture
    -0.46
    ĩ
    -0.46
    RISE
    -0.46
     gator
    -0.45
    POSITIVE LOGITS
    brainly
    0.58
     hagas
    0.57
    basicConfig
    0.56
    <bos>
    0.56
     kohta
    0.56
    ed
    0.52
    PhysRevLett
    0.52
     vanskelig
    0.51
    الحياه
    0.51
    ified
    0.51
    Activations Density 0.071%

    No Known Activations