© 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. 3486
    Prev
    Next
    INDEX
    Explanations

    mathematical operations and expressions involving addition and subtraction

    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
    chaff
    -0.70
    AccessFile
    -0.67
    Personendaten
    -0.61
     esternos
    -0.60
    下载附件
    -0.59
     sorgen
    -0.59
    bills
    -0.59
    errHandler
    -0.58
    Diagnostic
    -0.57
     GenerationType
    -0.57
    POSITIVE LOGITS
    Kaynakça
    0.61
    łku
    0.54
    PhysRevLett
    0.52
     فريبيس
    0.48
    PerformLayout
    0.46
    ύ
    0.46
    öf
    0.46
     kvinder
    0.46
    TargetApi
    0.45
     hendes
    0.44
    Activations Density 0.164%

    No Known Activations