© 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. 102
    Prev
    Next
    INDEX
    Explanations

    text within quotes or footnotes (citations)

    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
     myſelf
    -0.72
     Monfieur
    -0.71
     Jefus
    -0.69
     Theſe
    -0.69
     blest
    -0.61
     別注
    -0.61
     slums
    -0.59
     chofe
    -0.59
     ſhe
    -0.57
     canst
    -0.57
    POSITIVE LOGITS
    inter
    0.65
    in
    0.64
    dis
    0.64
    over
    0.62
    sur
    0.62
    con
    0.59
    inten
    0.59
    per
    0.59
    pro
    0.58
    comp
    0.58
    Activations Density 5.634%

    No Known Activations