© 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. 24-RES-MATRYOSHKA-DC
    7. 32
    Prev
    Next
    INDEX
    Explanations

    numbers within a document

    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.24.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.24.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
     feroit
    -0.85
     avoient
    -0.84
     démocr
    -0.81
     varandra
    -0.79
     auroit
    -0.79
     étoient
    -0.78
     colorés
    -0.78
     pouvoit
    -0.77
     normaux
    -0.77
     définiti
    -0.76
    POSITIVE LOGITS
     new
    0.28
     high
    0.27
     other
    0.27
     first
    0.27
     public
    0.27
     
    0.26
     second
    0.26
     short
    0.26
     more
    0.25
     full
    0.25
    Activations Density 99.041%

    No Known Activations