© 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
    2. Gemma-2-2B
    3. 5-CLT-HP
    4. 1937
    Prev
    Next
    INDEX
    Explanations

    than

    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
    principalColumn
    -0.75
     المعيارى
    -0.74
    
    -0.72
    ThroughAttribute
    -0.72
     BorderSide
    -0.70
     betweenstory
    -0.68
    expandindo
    -0.68
     Itself
    -0.68
    WEBPACK
    -0.66
    Hochspringen
    -0.66
    POSITIVE LOGITS
     are
    0.74
     do
    0.59
     correspond
    0.47
     komen
    0.43
     werden
    0.42
    %',
    0.42
     wirken
    0.42
     Do
    0.41
     corrispond
    0.41
    },[])
    0.40
    Activations Density 0.003%

    No Known Activations