© 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. 14356
    Prev
    Next
    INDEX
    Explanations

    references to a caster or sorcerer figure involved in magical or magical-sounding contexts

    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
    -0.53
    ęku
    -0.50
    haga
    -0.47
    MemoryWarning
    -0.47
     AppCompatTheme
    -0.47
    isons
    -0.47
     volume
    -0.47
    珊
    -0.46
    хай
    -0.45
     समीक्षाएं
    -0.45
    POSITIVE LOGITS
     caster
    2.23
     casters
    1.52
     Caster
    1.48
    caster
    1.22
    Caster
    1.21
     autorytatywna
    0.89
     slightest
    0.85
     castor
    0.81
    Personendaten
    0.80
    icillin
    0.77
    Activations Density 0.003%

    No Known Activations