© 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. 1712
    Prev
    Next
    INDEX
    Explanations

    biochemistry research papers with discussions of novel inhibitors and their solubility and activity

    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
     thừa
    -0.59
    }))
    -0.58
     wireType
    -0.55
    IntoConstraints
    -0.54
    ionados
    -0.49
    }],
    -0.48
     Befe
    -0.47
    AndEndTag
    -0.47
     internazionali
    -0.46
     Cool
    -0.46
    POSITIVE LOGITS
     Screening
    0.79
     screening
    0.77
     compounds
    0.75
     screened
    0.74
     screens
    0.74
     screen
    0.74
     Discovery
    0.71
     hits
    0.71
     Compounds
    0.71
     compound
    0.70
    Activations Density 0.908%

    No Known Activations