© 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
    2. Gemma-2-2B
    3. 18-RES-MATRYOSHKA-DC
    4. 48
    Prev
    Next
    INDEX
    Explanations

    file paths related to tex and lua

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.18.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.18.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
    )"),
    -0.79
    ']],
    -0.78
    _));
    -0.75
    '],
    
    -0.71
    "]];
    -0.70
    ']),
    -0.69
    ANCIAL
    -0.68
    ])));
    -0.68
    ERÍA
    -0.68
    ']);
    
    -0.66
    POSITIVE LOGITS
    ™
    0.66
    ®
    0.55
    ™,
    0.54
    ⓧ
    0.51
    ,
    0.50
     فريبيس
    0.47
     thingy
    0.47
     للمعارف
    0.47
    ™.
    0.47
     (
    0.46
    Activations Density 29.351%

    No Known Activations