© 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. 12-RES-MATRYOSHKA-DC
    7. 20174
    Prev
    Next
    INDEX
    Explanations

    specific measurements of concentrations in scientific contexts

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.12.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.12.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
     setId
    -0.57
    mybatisplus
    -0.56
    GenerationType
    -0.56
     sqlalchemy
    -0.56
    mazon
    -0.55
    jera
    -0.51
     GenerationType
    -0.51
    MathML
    -0.50
    IDENTIAL
    -0.50
    conio
    -0.50
    POSITIVE LOGITS
     ungu
    0.65
    发表于
    0.63
     cherchés
    0.63
     preſ
    0.63
     preci
    0.62
    middels
    0.62
    хьтан
    0.60
    省市镇
    0.59
    ArrowToggle
    0.59
     tartalomajánló
    0.57
    Activations Density 0.035%

    No Known Activations