© 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. 45645
    Prev
    Next
    INDEX
    Explanations

    potency

    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
     massive
    -1.05
    massive
    -0.90
    Massive
    -0.86
     Massive
    -0.85
     onCancelled
    -0.74
     powerful
    -0.71
     massively
    -0.67
     massiv
    -0.65
     ProtoMessage
    -0.62
     puissante
    -0.59
    POSITIVE LOGITS
    fony
    0.56
    árl
    0.55
    NameInMap
    0.54
    XmlAccessType
    0.54
     Happen
    0.52
    SourceChecksum
    0.52
     orgasm
    0.52
    atase
    0.51
     nebu
    0.50
     pistons
    0.49
    Activations Density 0.253%

    No Known Activations