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. 5-CLT-HP
    4. 95710
    Prev
    Next
    INDEX
    Explanations

    of

    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
     ujednoznacz
    -0.97
     InputDecoration
    -0.97
     '\\;'
    -0.93
    LookAnd
    -0.92
     صوتيه
    -0.91
    SPATH
    -0.91
    parsedMessage
    -0.90
    +#+#
    -0.89
    StoryboardSegue
    -0.89
    SourceChecksum
    -0.89
    POSITIVE LOGITS
     is
    0.42
     F
    0.34
     given
    0.34
     are
    0.33
    ವು
    0.32
    正是
    0.32
    幸いです
    0.32
    ACHI
    0.31
    ta
    0.31
    tager
    0.31
    Activations Density 0.025%

    No Known Activations