© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 5-CLT-HP
    4. 96409
    Prev
    Next
    INDEX
    Explanations

    practice/custom

    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
    '))
    
    -0.56
    }%
    -0.54
    )});
    -0.54
     ''}
    -0.52
     "")
    
    -0.51
     "'");
    -0.51
     */;
    -0.49
    ']);
    
    -0.48
     ejerc
    -0.48
     ""}
    -0.48
    POSITIVE LOGITS
    WriteTagHelper
    0.69
    gridx
    0.65
     AssemblyTitle
    0.63
    ModelAdmin
    0.63
    writeFieldEnd
    0.63
    DockStyle
    0.63
     iprot
    0.62
    EndProject
    0.62
    SerializedName
    0.61
     يتيمه
    0.61
    Activations Density 0.003%

    No Known Activations