© 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. 4516
    Prev
    Next
    INDEX
    Explanations

    references to data and comparisons to experimental results

    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
     Plan
    -0.54
     CGRect
    -0.49
    !*\
    -0.47
     estimés
    -0.47
    ///</
    -0.46
    AddTagHelper
    -0.45
    CGRectMake
    -0.45
    UnusedPrivate
    -0.44
    <%@
    -0.44
     plan
    -0.44
    POSITIVE LOGITS
    LLocation
    0.81
     Monfieur
    0.75
     Theſe
    0.70
     itſelf
    0.68
     Majefty
    0.66
     Anſ
    0.65
    ValueStyle
    0.65
     RSSSF
    0.64
    InputBorder
    0.64
     canst
    0.63
    Activations Density 0.604%

    No Known Activations