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. 9336
    Prev
    Next
    INDEX
    Explanations

    the letter 's' and its variations in different contexts, indicating a focus on the frequency of 's' occurrences within the text

    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
    Datuak
    -0.66
     intptr
    -0.64
    ậc
    -0.63
    andaag
    -0.61
    ampire
    -0.60
    robat
    -0.58
    Gizmos
    -0.58
    }^{+\
    -0.58
     ostavi
    -0.57
    HtmlAttribute
    -0.57
    POSITIVE LOGITS
     Cæsar
    0.67
    #+#
    0.64
     Infantil
    0.56
     parlement
    0.54
     commerciali
    0.54
     Сол
    0.52
     Sully
    0.52
     Shakspeare
    0.52
     męski
    0.50
    setSuccess
    0.50
    Activations Density 0.004%

    No Known Activations