© 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. 0-CLT-HP
    7. 91023
    Prev
    Next
    INDEX
    Explanations

    Reaching objectives

    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
     target
    -1.42
     Target
    -1.23
    Target
    -1.22
    target
    -1.21
     targets
    -1.01
     TARGET
    -0.90
    TARGET
    -0.80
     Targets
    -0.80
    targets
    -0.75
    目标
    -0.72
    POSITIVE LOGITS
    webElementXpaths
    0.98
     Normdatei
    0.89
    LookAnd
    0.84
    +#+#
    0.84
    تقاوى
    0.83
     myſelf
    0.83
     itſelf
    0.82
    الحياه
    0.76
    Jereo
    0.76
    SourceChecksum
    0.75
    Activations Density 0.024%

    No Known Activations