© 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. 1088
    Prev
    Next
    INDEX
    Explanations

    text that sounds like a scientific paper abstract

    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
     Pseudomonas
    -0.65
    IntoConstraints
    -0.60
     aureus
    -0.59
    harma
    -0.56
    ffindor
    -0.55
     '@/
    -0.54
    queo
    -0.54
    putan
    -0.53
     snippetHide
    -0.51
     aeruginosa
    -0.51
    POSITIVE LOGITS
     parasites
    0.81
     Paras
    0.78
     parasite
    0.78
     paras
    0.67
    pholes
    0.67
    Paras
    0.66
    paras
    0.63
     game
    0.62
     Try
    0.62
     Malaria
    0.62
    Activations Density 0.335%

    No Known Activations