© 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. 45125
    Prev
    Next
    INDEX
    Explanations

    cars

    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
    tvguidetime
    -0.75
     disponibilités
    -0.66
    urator
    -0.64
    QPalette
    -0.62
    urlopen
    -0.57
    Viki
    -0.55
    احب
    -0.53
    ANDUM
    -0.52
    hirkan
    -0.52
     Kej
    -0.52
    POSITIVE LOGITS
    ftagPool
    0.67
    ]));
    0.52
    ()]);
    0.52
     Bre
    0.47
    IVEREF
    0.47
    )]:
    0.47
     вікі
    0.47
     Dou
    0.46
    ungo
    0.46
    דש
    0.46
    Activations Density 0.273%

    No Known Activations