© 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
    2. Gemma-2-2B
    3. 1-CLT-HP
    4. 13070
    Prev
    Next
    INDEX
    Explanations

    names and online articles

    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
     Watson
    -1.42
    Watson
    -1.18
     WATSON
    -0.82
    tos
    -0.53
    /**
    -0.47
    roud
    -0.45
    WAT
    -0.44
    wat
    -0.44
    rew
    -0.43
     wat
    -0.42
    POSITIVE LOGITS
    IndentedString
    0.94
    Personendaten
    0.90
    GIVEREF
    0.83
     InputDecoration
    0.80
     HttpNotFound
    0.79
    parsedMessage
    0.78
    bewerken
    0.78
     '\\;'
    0.77
    addCriterion
    0.76
    AndEndTag
    0.71
    Activations Density 0.006%

    No Known Activations