© 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. 29705
    Prev
    Next
    INDEX
    Explanations

    keywords related to numerical counts or measurements

    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
     CanadaChoose
    -0.71
     figliu
    -0.68
     Efq
    -0.68
     quæ
    -0.67
    __).
    -0.67
    basicConfig
    -0.65
    (')
    -0.63
     '/';
    -0.62
     avoient
    -0.61
    })-\
    -0.61
    POSITIVE LOGITS
    idopsis
    0.62
     通販
    0.58
    Theoretical
    0.56
    oise
    0.56
    ený
    0.54
    apimachinery
    0.53
     hele
    0.52
    orite
    0.52
     cardinality
    0.52
    jolly
    0.52
    Activations Density 0.189%

    No Known Activations