© 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. 13746
    Prev
    Next
    INDEX
    Explanations

    shape

    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
    ])):
    -0.54
    aney
    -0.50
    veland
    -0.45
     Besøkt
    -0.45
    hibit
    -0.45
     résine
    -0.44
    wski
    -0.44
    })`
    -0.44
    fere
    -0.44
     aapt
    -0.43
    POSITIVE LOGITS
     CreateTagHelper
    0.65
    EndGlobalSection
    0.64
    ItemLayout
    0.63
     disruption
    0.61
     deformation
    0.60
     nahilalakip
    0.60
     shape
    0.59
     judgement
    0.58
    CloseOperation
    0.57
     plasticity
    0.57
    Activations Density 0.050%

    No Known Activations