© 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. 20-CLT-HP
    7. 72642
    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
     isComment
    -0.62
     }}"></
    -0.56
    />";
    -0.52
    ;}
    -0.52
    ública
    -0.52
    )]:
    -0.51
    AnchorStyles
    -0.51
     fhort
    -0.51
     quæ
    -0.49
    BackStack
    -0.49
    POSITIVE LOGITS
     el
    0.64
    rrggbb
    0.58
     незавершена
    0.56
     indisponible
    0.55
    Viitteet
    0.52
    MemoryWarning
    0.52
    richTextPanel
    0.50
    zość
    0.47
    esez
    0.45
    Uninitialized
    0.45
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.