© 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. 5953
    Prev
    Next
    INDEX
    Explanations

    me

    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
     almost
    -0.58
     ogóle
    -0.51
     casi
    -0.51
    เลย
    -0.50
     אלא
    -0.49
    ParallelGroup
    -0.48
     nearly
    -0.47
     even
    -0.46
    almost
    -0.45
    acyjnych
    -0.45
    POSITIVE LOGITS
    MessageTagHelper
    0.65
    }],
    0.58
     })
    0.57
    ;}
    0.56
     Alembic
    0.54
    }}/>
    0.54
    Aholisi
    0.53
     kaarangay
    0.52
    ']],
    0.50
     légales
    0.50
    Activations Density 0.009%

    No Known Activations