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. 20599
    Prev
    Next
    INDEX
    Explanations

    references to female characters or subjects in 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
    haustible
    -0.69
    styleType
    -0.58
    __(/*!
    -0.56
    Πηγές
    -0.54
     istrinya
    -0.54
    __).
    -0.53
     Normdatei
    -0.52
    olata
    -0.52
    
    -0.52
    aarrggbb
    -0.51
    POSITIVE LOGITS
     propOrder
    0.74
    WebServlet
    0.71
    she
    0.67
    Viitteet
    0.66
     JpaRepository
    0.66
     haar
    0.63
    She
    0.62
    mybatisplus
    0.60
    her
    0.59
    #+#
    0.58
    Activations Density 0.044%

    No Known Activations