© 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. 1073
    Prev
    Next
    INDEX
    Explanations

    apostrophes, periods, and whitespace preceded by letters or numbers.

    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
     للاسماء
    -0.80
    "';
    -0.64
    }))
    -0.62
    )$_
    -0.60
    $_.
    -0.59
    CodedInputStream
    -0.58
     الحره
    -0.58
    "}")
    -0.58
    bootstrapcdn
    -0.57
    thée
    -0.57
    POSITIVE LOGITS
     resourceCulture
    0.76
     continúas
    0.56
     disambiguazione
    0.53
     ProtoMessage
    0.52
    openzeppelin
    0.52
    Tembelea
    0.51
     estoppel
    0.50
    glLoadIdentity
    0.49
    leukin
    0.47
    eleste
    0.46
    Activations Density 0.624%

    No Known Activations