© 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. 876
    Prev
    Next
    INDEX
    Explanations

    text describing experimental results in a scientific paper

    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
    CppMethod
    -0.50
     tắt
    -0.49
     BoxFit
    -0.48
    突入
    -0.48
     decedent
    -0.47
    taux
    -0.46
     indor
    -0.45
    Gemeinden
    -0.44
    insertBefore
    -0.44
     Scroll
    -0.44
    POSITIVE LOGITS
     Atoms
    0.71
     Himo
    0.69
    HomeAsUpEnabled
    0.67
     Bond
    0.67
     atoms
    0.64
     angles
    0.63
     bond
    0.63
    bond
    0.63
    Bond
    0.61
     atom
    0.60
    Activations Density 0.325%

    No Known Activations