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. 15921
    Prev
    Next
    INDEX
    Explanations

    the mention of the name "Van" or its variations in different contexts

    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
     pleaſure
    -1.14
     nakalista
    -1.05
     myſelf
    -1.05
     itſelf
    -1.04
    +#+#
    -1.02
    })*/
    -1.02
     juſt
    -0.97
     reaſon
    -0.96
    enumi
    -0.94
    ViewFeatures
    -0.94
    POSITIVE LOGITS
     Van
    1.55
     van
    1.52
    Van
    1.43
     VAN
    1.39
    van
    1.22
     vans
    1.20
    VAN
    1.13
    vans
    0.87
     Vans
    0.86
    Vanessa
    0.81
    Activations Density 0.016%

    No Known Activations