© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 4612
    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
    ↵
    -0.52
    <eos>
    -0.50
     
    -0.49
    ↵↵
    -0.44
    ↵↵↵
    -0.42
    .
    -0.41
    ,
    -0.41
     and
    -0.40
     F
    -0.39
    ;
    -0.37
    POSITIVE LOGITS
     Мексичка
    1.45
     myſelf
    1.45
    LookAnd
    1.38
    Geplaatst
    1.36
    rungsseite
    1.36
     ſind
    1.34
     itſelf
    1.30
    ſelf
    1.30
     themſelves
    1.30
     Савезне
    1.28
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.