© 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. 0-RES-MATRYOSHKA-DC
    7. 13918
    Prev
    Next
    INDEX
    Explanations

    code related to casting spells or invoking specific spell functions

    oai_token-act-pair · gpt-4.1-nano
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     cast
    -0.79
    cast
    -0.67
     casting
    -0.66
     MotionEvent
    -0.62
    cherichia
    -0.58
     actionMode
    -0.58
    UnusedPrivate
    -0.56
     RoutedEventArgs
    -0.56
     DialogResult
    -0.55
    casting
    -0.54
    POSITIVE LOGITS
    Cast
    1.80
     Cast
    1.14
     Castor
    0.84
    centiles
    0.60
     sqlalchemy
    0.58
    testens
    0.57
     rerum
    0.57
    prefixer
    0.57
    hrt
    0.54
    }))
    0.53
    Activations Density 0.001%

    No Known Activations