Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 0-RES-MATRYOSHKA-DC
    4. 14430
    Prev
    Next
    INDEX
    Explanations

    regions or features associated with variable levels of a specific biological or chemical signal

    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
    vars
    -0.55
    .
    -0.45
    ’
    -0.43
    !
    -0.42
     stand
    -0.41
    Vars
    -0.40
    スタンド
    -0.39
     problem
    -0.39
    a
    -0.39
    I
    -0.39
    POSITIVE LOGITS
    ^(@)
    0.98
    SourceChecksum
    0.96
     FetchType
    0.92
    WithMany
    0.92
     LCCN
    0.88
     صوتيه
    0.83
    InputBorder
    0.82
    AsUp
    0.82
    Portale
    0.80
     насељу
    0.80
    Activations Density 0.020%

    No Known Activations