© 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. 3379
    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
    تقاوى
    -0.69
     hObject
    -0.59
    ResumeLayout
    -0.58
     اسب
    -0.53
    ấn
    -0.52
    principalColumn
    -0.51
    GeneratedValue
    -0.50
     useStyles
    -0.49
     Barna
    -0.48
     BrowserModule
    -0.47
    POSITIVE LOGITS
     how
    1.09
     How
    1.04
     what
    0.95
     why
    0.91
     What
    0.86
    How
    0.84
     Why
    0.82
    what
    0.81
     Does
    0.81
    how
    0.80
    Activations Density 0.000%

    No Known Activations