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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 1212
    Prev
    Next
    INDEX
    Explanations

    many

    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
    JspWriter
    -0.67
     ddelweddau
    -0.66
    bootstrapcdn
    -0.63
    GraphicsUnit
    -0.62
     الحره
    -0.58
    liesslich
    -0.58
    aarrggbb
    -0.57
    woordig
    -0.55
    InvalidProtocol
    -0.54
     OMITBAD
    -0.54
    POSITIVE LOGITS
     before
    0.67
     other
    0.63
     others
    0.60
    Datuak
    0.54
     semelhantes
    0.54
     similares
    0.51
     Walkover
    0.49
     semblables
    0.48
     før
    0.48
     similaires
    0.48
    Activations Density 0.003%

    No Known Activations