© 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. 2080
    Prev
    Next
    INDEX
    Explanations

    numbers and dates

    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
     ſtate
    -0.99
     purpoſe
    -0.98
     faſt
    -0.95
    ſelf
    -0.93
     Jefus
    -0.89
    ſelves
    -0.86
     ſmall
    -0.85
     itſelf
    -0.85
     myſelf
    -0.84
     reaſon
    -0.83
    POSITIVE LOGITS
    WebElementEntity
    0.50
    qtype
    0.49
    osp
    0.48
    ┛
    0.47
    ╝
    0.45
    —
    0.45
     op
    0.44
    ঐ
    0.44
    9
    0.43
    -
    0.42
    Activations Density 0.002%

    No Known Activations