© 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. 12-RES-MATRYOSHKA-DC
    7. 4346
    Prev
    Next
    INDEX
    Explanations

    text related to technology and gadgets

    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
    ogly
    -0.54
     ProtoMessage
    -0.49
    туга
    -0.49
     METHOD
    -0.49
    PhysRevD
    -0.49
     Method
    -0.48
    Lähteet
    -0.47
    layoutControl
    -0.47
     method
    -0.47
    timeZone
    -0.45
    POSITIVE LOGITS
     purposes
    0.65
     intptr
    0.62
     saites
    0.60
     Purposes
    0.59
    PreferredItem
    0.57
     üzere
    0.55
     Efq
    0.54
    用に
    0.54
     向け
    0.54
     Kays
    0.53
    Activations Density 1.406%

    No Known Activations