© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 97631
    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
     SSM
    -0.66
     PSM
    -0.60
    ailleurs
    -0.59
     ―――――
    -0.59
     Empieza
    -0.58
    ACIAS
    -0.58
     AppColors
    -0.57
     Efq
    -0.57
     Cæsar
    -0.55
    зулта
    -0.54
    POSITIVE LOGITS
    GraphicsUnit
    0.60
    DeleteBehavior
    0.59
     Exacts
    0.58
     utafitiHapana
    0.55
     rêves
    0.54
     juridiques
    0.52
    Handlung
    0.52
    TypedDataSet
    0.51
     nakalista
    0.51
     funcionales
    0.49
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.