© 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. 525
    Prev
    Next
    INDEX
    Explanations

    references to user action

    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
     Were
    -0.63
    Were
    -0.62
    pides
    -0.57
     Did
    -0.49
    Did
    -0.49
    twimg
    -0.46
    itonitis
    -0.46
     WERE
    -0.45
    的是
    -0.44
    were
    -0.44
    POSITIVE LOGITS
     can
    2.91
     could
    2.09
    can
    1.93
    Can
    1.68
     bisa
    1.66
     dapat
    1.64
     Can
    1.60
     kann
    1.60
    could
    1.58
     können
    1.55
    Activations Density 1.433%

    No Known Activations