© 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. 8827
    Prev
    Next
    INDEX
    Explanations

    expressions of understanding or lack thereof, often associated with knowledge or capability

    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
    opsida
    -0.59
     "..\..\..\
    -0.57
    RegressionTest
    -0.55
    omock
    -0.54
     unknownFields
    -0.51
    ="{{$
    -0.49
    tigas
    -0.49
     disambiguazione
    -0.49
     للمعارف
    -0.49
    encodeWith
    -0.48
    POSITIVE LOGITS
     neither
    0.98
     nothing
    0.94
    AnchorStyles
    0.90
    neither
    0.88
     none
    0.87
     żad
    0.84
     aucune
    0.81
     no
    0.81
     nowhere
    0.80
     Neither
    0.80
    Activations Density 0.117%

    No Known Activations