© 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. 2063
    Prev
    Next
    INDEX
    Explanations

    hard

    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
    ArrowToggle
    -0.73
    CloseOperation
    -0.66
    ReusableCell
    -0.65
    ✨:
    -0.65
     propOrder
    -0.63
    endforeach
    -0.63
     rhestr
    -0.62
     doInBackground
    -0.62
     /\.
    -0.62
    ölkerung
    -0.62
    POSITIVE LOGITS
    }),
    0.45
    ★★★★☆
    0.45
    igshid
    0.44
    érons
    0.43
     constat
    0.43
     apon
    0.42
     IMDG
    0.42
    LayoutStyle
    0.42
    ofla
    0.41
    makeText
    0.41
    Activations Density 0.008%

    No Known Activations