© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 11090
    Prev
    Next
    INDEX
    Explanations

    references to experimental materials and methods

    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
    Datuak
    -0.60
     ]);
    -0.55
    出版年
    -0.54
     précédents
    -0.54
     avoient
    -0.53
     devront
    -0.51
    msup
    -0.51
    ,:);
    -0.50
     précédentes
    -0.50
     précédemment
    -0.49
    POSITIVE LOGITS
    featureID
    0.73
    CloseOperation
    0.65
    InjectAttribute
    0.63
    kháu
    0.63
     defStyle
    0.62
    cdef
    0.59
    execSQL
    0.58
    LayoutConstraint
    0.57
     Référence
    0.55
    ImageContext
    0.55
    Activations Density 0.005%

    No Known Activations