© 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. 5-CLT-HP
    7. 2013
    Prev
    Next
    INDEX
    Explanations

    follow

    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
    +#+#
    -0.84
    msgTypes
    -0.74
    UnsafeEnabled
    -0.71
     InputDecoration
    -0.71
     BoxDecoration
    -0.65
    ParallelGroup
    -0.64
    InputBorder
    -0.64
    ("")]
    -0.63
    GenerationType
    -0.61
    bootstrapcdn
    -0.61
    POSITIVE LOGITS
     only
    0.52
    óta
    0.49
    Only
    0.48
    Permalink
    0.44
     compare
    0.43
     always
    0.42
    awsze
    0.42
     root
    0.42
     probably
    0.41
    only
    0.41
    Activations Density 0.002%

    No Known Activations