© 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. 8660
    Prev
    Next
    INDEX
    Explanations

    terms related to numerical values and constraints

    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
     мѣ
    -0.87
     Paine
    -0.80
     }}">
    -0.79
    Etimología
    -0.78
    انجليز
    -0.76
    '));
    -0.75
    czegó
    -0.75
    oooooooooooooooo
    -0.74
    \}}
    -0.72
    }}}{\
    -0.71
    POSITIVE LOGITS
     MessageBoxIcon
    0.68
    PageIndex
    0.67
    httphttps
    0.67
     yonder
    0.64
    HOUT
    0.59
     CrossRef
    0.58
     brady
    0.58
    Boas
    0.58
     validamos
    0.57
    yaszt
    0.56
    Activations Density 0.004%

    No Known Activations