© 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
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 97040
    Prev
    Next
    INDEX
    Explanations

    Ab

    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
     Ab
    -1.25
     ab
    -0.98
    Ab
    -0.98
     planning
    -0.71
    s
    -0.60
     assessment
    -0.59
     screening
    -0.54
     v
    -0.53
     am
    -0.52
    ↵
    -0.51
    POSITIVE LOGITS
     myſelf
    1.16
     Majefty
    1.09
     itſelf
    1.03
     pleaſure
    1.03
     purpoſe
    1.02
    IntoConstraints
    1.02
    SBATCH
    0.98
     themſelves
    0.96
     ſche
    0.95
     ―――――
    0.92
    Activations Density 0.133%

    No Known Activations