© 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. 24648
    Prev
    Next
    INDEX
    Explanations

    numerical values and references to case citations

    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
     WL
    -0.58
    WL
    -0.53
     mas
    -0.50
     Ant
    -0.47
     R
    -0.47
     and
    -0.44
     des
    -0.44
     
    -0.44
     r
    -0.43
    ow
    -0.43
    POSITIVE LOGITS
     الحره
    0.99
     незавершена
    0.85
     Савезне
    0.81
    InitVars
    0.79
     avoient
    0.79
     nahilalakip
    0.79
    twimg
    0.77
     étoit
    0.75
     Cæsar
    0.75
     itſelf
    0.75
    Activations Density 0.004%

    No Known Activations