© 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. 746
    Prev
    Next
    INDEX
    Explanations

    gene or researcher names

    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
     raiſ
    -1.49
     Efq
    -1.45
     myſelf
    -1.42
     ―――――
    -1.39
     Theſe
    -1.36
     Houſe
    -1.34
     itſelf
    -1.31
     Monfieur
    -1.30
     Jefus
    -1.27
     $_(
    -1.26
    POSITIVE LOGITS
     
    0.78
     Mas
    0.72
     Har
    0.71
     Bal
    0.71
    ↵↵
    0.70
     Ro
    0.69
     Ber
    0.69
     Sal
    0.69
    .
    0.69
     Ar
    0.68
    Activations Density 2.301%

    No Known Activations