Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 12-RES-MATRYOSHKA-DC
    4. 14958
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "wizard."

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.12.hook_resid_post
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    32,768
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    chanind/pile-uncopyrighted-gemma-1024-abbrv-1B
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     خارجية
    -0.90
     مشين
    -0.85
    contentLoaded
    -0.79
     Abp
    -0.75
     Ophelia
    -0.74
     ModelExpression
    -0.74
     BNE
    -0.73
    Personensuche
    -0.73
     '\\;'
    -0.73
    Valentina
    -0.73
    POSITIVE LOGITS
     Wizard
    1.33
     wizard
    1.21
    Wizard
    1.18
     wizards
    1.18
     Wizards
    1.08
    wizard
    1.00
    Wiz
    0.93
    wiz
    0.90
     Wiz
    0.88
     Whi
    0.80
    Activations Density 0.004%

    No Known Activations