© 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. 44188
    Prev
    Next
    INDEX
    Explanations

    embedding, kits

    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
    Sequence
    -0.87
     sequence
    -0.85
    sequence
    -0.85
    seq
    -0.84
     Sequence
    -0.77
     seq
    -0.68
     sequences
    -0.63
    SEQUENCE
    -0.62
    Seq
    -0.61
     SEQUENCE
    -0.61
    POSITIVE LOGITS
     Monfieur
    1.05
     Efq
    0.93
     purpoſe
    0.93
     AssemblyCulture
    0.88
     doubtnut
    0.85
     myſelf
    0.83
     houſe
    0.81
    principalTable
    0.80
    XMLSchema
    0.77
     Houſe
    0.76
    Activations Density 0.683%

    No Known Activations