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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 0-RES-MATRYOSHKA-DC
    4. 14042
    Prev
    Next
    INDEX
    Explanations

    references to a specific word indicating a downward movement or direction

    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
    LookAnd
    -0.96
     femininas
    -0.85
    TagMode
    -0.73
     FetchType
    -0.68
     russes
    -0.64
    ıntı
    -0.63
     VizieR
    -0.63
     مصرى
    -0.61
    InputBorder
    -0.61
     barbati
    -0.60
    POSITIVE LOGITS
     Down
    1.99
    Down
    1.84
    DOWN
    0.98
     DOWN
    0.85
     Downs
    0.76
     Up
    0.66
     Downing
    0.60
    jsonwebtoken
    0.58
     Common
    0.55
    XmlAccessType
    0.55
    Activations Density 0.001%

    No Known Activations