© 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. 24-RES-MATRYOSHKA-DC
    7. 964
    Prev
    Next
    INDEX
    Explanations

    measurements and significant digits

    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.24.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.24.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
    lapsingToolbar
    -0.69
    parsedMessage
    -0.54
     reposer
    -0.53
     kaarangay
    -0.51
    addCriterion
    -0.50
     prove
    -0.50
    ẖ
    -0.49
     HasFactory
    -0.48
    ScopeManager
    -0.47
    spanning
    -0.47
    POSITIVE LOGITS
     nearest
    1.19
    nearest
    1.03
     Nearest
    1.01
    Nearest
    0.97
     tenths
    0.84
     rounding
    0.79
     rounded
    0.75
     accuracy
    0.74
     hund
    0.72
     closest
    0.71
    Activations Density 0.208%

    No Known Activations