© 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. 5956
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    <bos>
    -0.88
     يتيمه
    -0.66
     onCreateView
    -0.65
     nakalista
    -0.65
    RegistryLite
    -0.64
    styleable
    -0.62
    RegressionTest
    -0.60
    ArrowToggle
    -0.59
    Referanser
    -0.59
    Lähteet
    -0.58
    POSITIVE LOGITS
     (
    0.64
     +
    0.46
     objection
    0.45
    Obvious
    0.45
    DONE
    0.44
    >>>>>>>
    0.44
     ditch
    0.42
     linkovi
    0.41
     IRL
    0.41
     -
    0.41
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.