© 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. 0-CLT-HP
    7. 95706
    Prev
    Next
    INDEX
    Explanations

    technical documents

    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
     rub
    -0.81
     Emp
    -0.75
     emp
    -0.73
    Emp
    -0.66
     EMP
    -0.63
    emp
    -0.60
     rubric
    -0.58
    EMP
    -0.56
    发表于
    -0.51
    AxisAlignment
    -0.51
    POSITIVE LOGITS
     itſelf
    0.70
     Jefus
    0.68
     myſelf
    0.65
     betweenstory
    0.64
     Theſe
    0.64
     дописавши
    0.61
    évaluateur
    0.59
     Económica
    0.59
     referenties
    0.59
     becauſe
    0.59
    Activations Density 0.110%

    No Known Activations