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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 9-RES-MATRYOSHKA-DC
    4. 16506
    Prev
    Next
    INDEX
    Explanations

    the word "storage" and words that include it, within a code context

    oai_token-act-pair · gemini-2.0-flash
    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
    tagHelperRunner
    -1.21
    +#+#
    -1.21
     Majefty
    -0.94
    modelBuilder
    -0.93
     Monfieur
    -0.92
    CloseOperation
    -0.90
     externi
    -0.90
    +#+
    -0.90
    FieldNumber
    -0.90
     Phon
    -0.89
    POSITIVE LOGITS
    STORAGE
    0.85
    getStorage
    0.73
     
    0.68
    Storage
    0.68
     I
    0.67
    ICOS
    0.67
    RIOS
    0.67
     tan
    0.66
     Delgado
    0.65
     Storage
    0.65
    Activations Density 0.019%

    No Known Activations