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-CLT-HP
    4. 795
    Prev
    Next
    INDEX
    Explanations

    assumed

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    IndentedString
    -0.92
     Highway
    -0.91
     snippetHide
    -0.91
    Highway
    -0.91
     raiſ
    -0.90
     myſelf
    -0.89
    ReusableCell
    -0.86
     itſelf
    -0.86
     Jefus
    -0.84
     Shaksp
    -0.84
    POSITIVE LOGITS
     to
    0.65
    to
    0.54
     
    0.52
     Cap
    0.49
     man
    0.45
     Man
    0.44
    Cap
    0.44
    ,
    0.43
     To
    0.42
     pers
    0.42
    Activations Density 0.172%

    No Known Activations