© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-RES-MATRYOSHKA-DC
    7. 90
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions, especially algebraic equations and functions.

    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.22.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.22.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
     ProtoMessage
    -0.91
    ()))
    -0.86
    _));
    -0.80
    '))
    -0.79
     CURIAM
    -0.78
    extAlignment
    -0.77
    "]);
    -0.76
    ()));
    -0.75
     ]
    -0.75
    _
    -0.75
    POSITIVE LOGITS
     +
    0.92
     -
    0.82
     (-
    0.69
    (-
    0.66
     negative
    0.61
    +
    0.57
     minus
    0.54
    *
    0.54
     plus
    0.54
    /(
    0.53
    Activations Density 6.661%

    No Known Activations