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. 22660
    Prev
    Next
    INDEX
    Explanations

    formal legal terminology and expressions

    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
     Normdatei
    -0.69
    RenderAtEndOf
    -0.67
    MLLoader
    -0.61
    epiece
    -0.60
    astify
    -0.58
    printStackTrace
    -0.57
    StoryboardSegue
    -0.57
    DrawerToggle
    -0.54
    OptionsMenu
    -0.53
    UnsafeEnabled
    -0.53
    POSITIVE LOGITS
     />";
    0.57
     Rumuni
    0.56
    rouvez
    0.55
    hésite
    0.50
    attendre
    0.50
    ℤ
    0.49
    ≦)
    0.47
    }>;
    0.47
    مراجع
    0.46
    ()?;
    0.45
    Activations Density 0.019%

    No Known Activations