© 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. 20-CLT-HP
    7. 74701
    Prev
    Next
    INDEX
    Explanations

    Technical texts

    np_max-act-logits · 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
    Geplaatst
    -0.66
    \{\\
    -0.60
    fillType
    -0.57
    PerformLayout
    -0.56
    LayoutPanel
    -0.55
    thmus
    -0.54
    TemporalType
    -0.52
    AndroidJUnit
    -0.52
     Lack
    -0.51
     <>",
    -0.49
    POSITIVE LOGITS
     back
    0.75
     otomatig
    0.74
    BACK
    0.58
     skill
    0.58
     skills
    0.57
     teacher
    0.56
    back
    0.55
     Back
    0.54
    Back
    0.53
     physician
    0.53
    Activations Density 0.000%

    No Known Activations