© 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. 2074
    Prev
    Next
    INDEX
    Explanations

    to

    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
    setVerticalGroup
    -0.84
    KommentareTeilen
    -0.77
     arşivlendi
    -0.74
    ########.
    -0.73
    сылкі
    -0.73
    tvguidetime
    -0.73
    AutoresizingMask
    -0.71
    )‏
    -0.70
     appunto
    -0.70
    findpost
    -0.69
    POSITIVE LOGITS
    avantage
    0.39
     controlling
    0.38
     control
    0.37
     sur
    0.35
     sup
    0.35
    JAKARTA
    0.35
     pose
    0.34
    kháu
    0.33
    手が
    0.33
     amb
    0.32
    Activations Density 0.552%

    No Known Activations