© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 6423
    Prev
    Next
    INDEX
    Explanations

    the names and details of directors and their works in film

    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
    dostęp
    -0.57
     vives
    -0.53
    qvarna
    -0.50
     ilegal
    -0.50
     tkinter
    -0.50
    Ї
    -0.48
     públicos
    -0.46
    ív
    -0.44
    oxidants
    -0.44
    entennial
    -0.44
    POSITIVE LOGITS
    +#+
    0.85
     AssemblyTitle
    0.73
    aarrggbb
    0.67
     estekak
    0.65
    Scénario
    0.62
     <=",
    0.62
    thâu
    0.61
     pinulongan
    0.60
    findpost
    0.59
    oredCriteria
    0.59
    Activations Density 0.238%

    No Known Activations