© 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. 5-CLT-HP
    7. 91096
    Prev
    Next
    INDEX
    Explanations

    has

    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
     happen
    -0.54
     Occur
    -0.48
     dauern
    -0.47
     ocor
    -0.45
    plona
    -0.45
    FontOfSize
    -0.44
     TextAlign
    -0.42
    Raycast
    -0.42
     Überg
    -0.41
    happen
    -0.41
    POSITIVE LOGITS
     EconPapers
    0.82
    StoryboardSegue
    0.79
     GenerationType
    0.74
    rawDesc
    0.68
    Personendaten
    0.66
    fjspx
    0.60
    QMetaType
    0.60
     LCCN
    0.60
    InteropServices
    0.58
    AndEndTag
    0.58
    Activations Density 0.001%

    No Known Activations