© 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. 0-CLT-HP
    7. 38857
    Prev
    Next
    INDEX
    Explanations

    received

    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
     received
    -1.94
    received
    -1.66
     receives
    -1.48
     recieved
    -1.47
     receive
    -1.41
     Received
    -1.41
     recibido
    -1.37
     ricevuto
    -1.35
    receive
    -1.31
    Received
    -1.30
    POSITIVE LOGITS
     the
    0.97
     a
    0.94
     an
    0.88
     its
    0.75
     by
    0.66
     his
    0.65
    s
    0.63
     multiple
    0.62
     three
    0.61
     ‘
    0.60
    Activations Density 0.051%

    No Known Activations