© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-RES-MATRYOSHKA-DC
    7. 13805
    Prev
    Next
    INDEX
    Explanations

    references to the word "forward," typically used in laboratory or experimental contexts

    oai_token-act-pair · gpt-4.1-nano
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ArrowToggle
    -0.79
     Wiktionnaire
    -0.70
     BoxFit
    -0.68
     LoginComponent
    -0.67
     AssemblyProduct
    -0.67
    errHandler
    -0.66
    MessageTagHelper
    -0.66
     SwitchCompat
    -0.65
    cestershire
    -0.65
    #+#
    -0.64
    POSITIVE LOGITS
    forward
    1.87
    FORWARD
    1.29
    Forward
    1.21
     forwarding
    0.71
     Forward
    0.69
    fwd
    0.67
     FORWARD
    0.56
     pasto
    0.53
    نش
    0.52
    Datuak
    0.50
    Activations Density 0.002%

    No Known Activations