© 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. 45156
    Prev
    Next
    INDEX
    Explanations

    Bem

    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
     Bem
    -0.96
    Bem
    -0.84
    llium
    -0.81
     bem
    -0.73
    fjspx
    -0.54
    ikk
    -0.52
     Ut
    -0.52
    bem
    -0.50
    ever
    -0.49
     satisfaire
    -0.49
    POSITIVE LOGITS
     doInBackground
    0.54
    ambilan
    0.54
    PreferredItem
    0.51
    -};
    0.50
    invokeLater
    0.50
    IndentedString
    0.48
    orescence
    0.48
    InvalidProtocol
    0.48
    Passcode
    0.47
     corti
    0.46
    Activations Density 0.375%

    No Known Activations