© 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. 22-RES-MATRYOSHKA-DC
    7. 2642
    Prev
    Next
    INDEX
    Explanations

    research related to drug-induced conditions and chemical compounds

    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.22.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.22.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
     gene
    -0.41
     genes
    -0.40
     sa
    -0.40
    cellor
    -0.40
     dans
    -0.40
    с
    -0.40
    washingtonpost
    -0.39
    Is
    -0.39
     constant
    -0.38
     Is
    -0.38
    POSITIVE LOGITS
    induced
    0.92
    Personendaten
    0.90
    IndentedString
    0.89
     Induced
    0.89
    Induced
    0.88
    localctx
    0.86
    treatment
    0.86
     induced
    0.85
     صوتيه
    0.85
     myſelf
    0.83
    Activations Density 0.382%

    No Known Activations