© 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. 18-RES-MATRYOSHKA-DC
    7. 40
    Prev
    Next
    INDEX
    Explanations

    code snippets and sequences

    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.18.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.18.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
    MTT
    -0.57
     SBR
    -0.49
    īts
    -0.47
    MCT
    -0.47
     Esprit
    -0.47
    ttl
    -0.47
    HNO
    -0.46
    oulli
    -0.46
     appunt
    -0.45
    FBS
    -0.44
    POSITIVE LOGITS
     genes
    1.10
     gene
    1.09
     genomic
    1.05
     genetic
    1.02
     mutations
    1.01
     genome
    1.01
     sequence
    0.92
     mutated
    0.92
     deletion
    0.92
     mutation
    0.91
    Activations Density 8.089%

    No Known Activations