© 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. 22-RES-MATRYOSHKA-DC
    7. 844
    Prev
    Next
    INDEX
    Explanations

    logging code and error messages

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.22.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.22.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
     Normdatei
    -0.63
    fjspx
    -0.51
    abancı
    -0.51
    Obrázky
    -0.47
    Portail
    -0.46
    TargetException
    -0.46
    StoryboardSegue
    -0.46
    विक
    -0.45
    nmgp
    -0.45
    VIAF
    -0.44
    POSITIVE LOGITS
     print
    1.58
     prints
    1.48
     Print
    1.45
     PRINT
    1.41
    print
    1.39
     printing
    1.34
     printed
    1.32
    Print
    1.30
    打印
    1.30
     debug
    1.27
    Activations Density 1.038%

    No Known Activations