© 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
    3. Gemma-2-2B
    5. 0-RES-MATRYOSHKA-DC
    7. 13908
    Prev
    Next
    INDEX
    Explanations

    code-related tokens, specifically variations of 'put' and 'PUT' in different key codes

    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
    _{-
    -0.81
    adaptiveStyles
    -0.64
    }")
    -0.63
    _{-\
    -0.61
    }_{-
    -0.60
    []
    -0.54
    lloworld
    -0.53
    ExecuteReader
    -0.52
    '}>
    -0.52
    LAHOMA
    -0.52
    POSITIVE LOGITS
    put
    2.09
    PUT
    1.42
    putString
    0.85
    puter
    0.82
    putInt
    0.70
    putation
    0.60
    putBoolean
    0.60
    devamını
    0.60
    putAll
    0.57
    multer
    0.55
    Activations Density 0.002%

    No Known Activations