© 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. 411
    Prev
    Next
    INDEX
    Explanations

    research papers and scientific writing, especially biology

    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
     Siehe
    -0.56
     Every
    -0.55
     every
    -0.54
    Every
    -0.53
     you
    -0.52
     tarvit
    -0.52
    every
    -0.52
    voorbeeld
    -0.51
     You
    -0.51
     Everything
    -0.51
    POSITIVE LOGITS
     our
    1.01
     Interestingly
    0.81
    our
    0.81
     متعلقه
    0.81
    Our
    0.79
    Interestingly
    0.79
     interestingly
    0.79
     previous
    0.77
     Our
    0.76
     ourselves
    0.73
    Activations Density 2.936%

    No Known Activations