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. 21-GEMMASCOPE-TRANSCODER-16K
    4. 5872
    Prev
    Next
    INDEX
    Explanations

    first person pronouns combined with expressions of personal thoughts, needs, or feelings or mental toughness

    oai_token-act-pair · gemini-2.0-flash

    phrases related to self-encouragement and resilience

    np_token-act-pair-logits · gpt-4o-mini
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope/layer_21/width_16k
    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
    CloseOperation
    -0.77
     كومونز
    -0.65
    findpost
    -0.65
     chande
    -0.64
     ISNI
    -0.64
    FieldBuilder
    -0.62
    SourceChecksum
    -0.60
    
    -0.59
    DllImport
    -0.59
    roli
    -0.57
    POSITIVE LOGITS
    Personendaten
    0.48
     treasure
    0.47
     <<<<<<<<<<<<<<
    0.46
    práv
    0.45
     arşivlendi
    0.43
    treasure
    0.41
    AndEndTag
    0.41
    赘
    0.41
     just
    0.40
     treasures
    0.39
    Activations Density 1.177%

    No Known Activations