© 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. 91000
    Prev
    Next
    INDEX
    Explanations

    }}"

    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
    tology
    -1.29
    jupiter
    -0.55
    院
    -0.51
    bilisi
    -0.49
    nvm
    -0.48
    цо
    -0.47
     }],
    -0.47
    GetInstance
    -0.47
    >>;
    -0.47
    RemoteException
    -0.46
    POSITIVE LOGITS
    PyExc
    0.85
     AspNetCore
    0.69
     يتيمه
    0.68
    StructEnd
    0.68
    ArrowToggle
    0.63
    elemField
    0.60
     فريبيس
    0.59
    género
    0.58
     TabLayout
    0.58
     تضيفلها
    0.57
    Activations Density 0.107%

    No Known Activations