© 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. 91438
    Prev
    Next
    INDEX
    Explanations

    course

    np_max-act · gemini-2.0-flash
    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
    yntaxException
    -0.57
     MPS
    -0.56
     besti
    -0.53
    NameInMap
    -0.53
     Nadie
    -0.52
    TargetException
    -0.52
    ิลป
    -0.52
     Sealed
    -0.51
     Abschluss
    -0.50
     monop
    -0.50
    POSITIVE LOGITS
    Viitteet
    0.55
     onOptions
    0.54
    Rujuakan
    0.53
    EReference
    0.53
    InstanceState
    0.51
    offsetTop
    0.51
     通販
    0.48
    Nuorodos
    0.48
     réservé
    0.48
    abbix
    0.48
    Activations Density 0.000%

    No Known Activations