© 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. 24604
    Prev
    Next
    INDEX
    Explanations

    phrases indicating conclusions or data summaries

    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
     muestra
    -0.51
     ایش
    -0.49
    ptest
    -0.48
     flaring
    -0.46
     jsonify
    -0.45
    feinander
    -0.45
    }?>
    -0.45
    monte
    -0.44
     vicin
    -0.44
    Fixture
    -0.44
    POSITIVE LOGITS
    featureID
    0.84
    parsedMessage
    0.84
     nahilalakip
    0.84
     متعلقه
    0.70
     Walkover
    0.70
     سكانية
    0.69
    下载附件
    0.69
    uxxxx
    0.68
     Италијани
    0.68
    MessageTagHelper
    0.67
    Activations Density 0.017%

    No Known Activations