© 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. 77433
    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
    ArgsConstructor
    -0.88
     InputDecoration
    -0.61
     '\\;'
    -0.58
    SpringBootTest
    -0.56
    ftagPool
    -0.54
     kasarigan
    -0.51
    Vidite
    -0.51
    ::_('
    -0.50
    QMetaType
    -0.50
    cia
    -0.49
    POSITIVE LOGITS
    //
    0.54
    /**
    0.54
    LOYEES
    0.49
    findpost
    0.48
    UrlResolution
    0.43
    aksana
    0.43
    ]")]
    0.42
     незавершена
    0.42
    ydd
    0.42
    ngrx
    0.41
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.