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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-CLT-HP
    7. 1368
    Prev
    Next
    INDEX
    Explanations

    recirc

    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
    efa
    -0.46
    epar
    -0.45
     eventdata
    -0.45
    addContainerGap
    -0.44
    شهاد
    -0.43
     endwhile
    -0.42
    endwhile
    -0.42
     endfor
    -0.42
    getMenuInflater
    -0.42
    ARAN
    -0.41
    POSITIVE LOGITS
    WriteBarrier
    0.65
     Meksiku
    0.58
     AssemblyProduct
    0.56
     mukana
    0.54
    ambito
    0.53
    tréal
    0.53
    utel
    0.53
     móvel
    0.53
    جوايز
    0.51
     Dont
    0.51
    Activations Density 0.003%

    No Known Activations