© 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. 8483
    Prev
    Next
    INDEX
    Explanations

    negative values or expressions related to loss

    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
    ⓧ
    -0.57
    "}\
    -0.56
    spesies
    -0.54
     näh
    -0.52
    Referencias
    -0.52
    PageFactory
    -0.50
     ']
    -0.49
     viewDidLoad
    -0.49
     }{@
    -0.48
    ()){
    -0.48
    POSITIVE LOGITS
    <bos>
    0.65
    argout
    0.63
    BagLayout
    0.60
    HexString
    0.57
    ellido
    0.56
     pinulongan
    0.56
    GIVEREF
    0.55
    LEncoder
    0.54
     صوتيه
    0.54
    ruppen
    0.53
    Activations Density 0.015%

    No Known Activations