© 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. 1-RES-MATRYOSHKA-DC
    7. 868
    Prev
    Next
    INDEX
    Explanations

    references to investigations or inquiries

    oai_token-act-pair · gpt-4.1-nano
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tosa
    -0.55
    antMatchers
    -0.53
    Prat
    -0.51
    ":[{
    -0.50
    extAlignment
    -0.50
    flashdata
    -0.50
     Prat
    -0.49
    SequentialGroup
    -0.49
     terci
    -0.49
    Xaml
    -0.48
    POSITIVE LOGITS
     investigate
    3.50
     investigated
    3.45
     investigation
    3.41
     Investigation
    3.31
     investigating
    3.25
     investigations
    3.22
     investigates
    3.20
    Investig
    3.19
    investig
    3.19
     Investigate
    3.16
    Activations Density 1.891%

    No Known Activations