© 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
    2. Gemma-2-2B
    3. 5-CLT-HP
    4. 90916
    Prev
    Next
    INDEX
    Explanations

    s

    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
    iprot
    -0.56
     rhestr
    -0.55
     ویکی‌پدیای
    -0.53
     Baptists
    -0.52
    illoma
    -0.52
     Insertion
    -0.52
    mpz
    -0.51
     Relaciones
    -0.50
     lids
    -0.49
    EDGE
    -0.49
    POSITIVE LOGITS
    AnchorStyles
    0.66
    **/
    
    0.57
    $}}
    0.53
     '))
    0.50
    MessageTagHelper
    0.49
    $
    
    0.49
     !$
    0.49
    }}}}
    0.47
    })).
    0.47
    TargetException
    0.47
    Activations Density 0.000%

    No Known Activations