© 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. 257
    Prev
    Next
    INDEX
    Explanations

    molecules related to organic chemistry

    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
    volution
    -0.48
     sez
    -0.48
    room
    -0.47
     Meksiku
    -0.47
    ropoda
    -0.46
     room
    -0.45
     event
    -0.45
     settings
    -0.44
     topo
    -0.44
    manship
    -0.43
    POSITIVE LOGITS
    Portale
    0.71
    期刊论文
    0.71
     onCancelled
    0.69
     Derivatives
    0.68
     derivative
    0.66
     derivatives
    0.64
     hydrochloride
    0.64
     Derivative
    0.63
    RectangleBorder
    0.63
     chi̍t
    0.63
    Activations Density 2.381%

    No Known Activations