© 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. 4-CLT-HP
    7. 4577
    Prev
    Next
    INDEX
    Explanations

    Locations

    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
     capturing
    -0.55
     genommen
    -0.54
    حوالہ
    -0.53
     ifrån
    -0.52
     collected
    -0.52
    collected
    -0.51
    EDEFAULT
    -0.51
     documenting
    -0.50
    記録
    -0.50
     memer
    -0.50
    POSITIVE LOGITS
     "..\..\..\
    0.68
    ]--;
    0.67
    AndEndTag
    0.66
     Normdatei
    0.65
    AddTagHelper
    0.65
    DockStyle
    0.64
    astify
    0.63
    ExtendWith
    0.62
     فريبيس
    0.61
    WriteAttribute
    0.60
    Activations Density 0.011%

    No Known Activations