© 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. 4-CLT-HP
    7. 4414
    Prev
    Next
    INDEX
    Explanations

    physically

    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
     препратки
    -0.61
    WriteTagHelper
    -0.61
    MenuInflater
    -0.57
    τως
    -0.56
     liability
    -0.56
     steeply
    -0.56
     optimally
    -0.55
    audiovisuel
    -0.55
    tvguidetime
    -0.54
    här
    -0.54
    POSITIVE LOGITS
    DebuggerNonUser
    0.63
     see
    0.54
     CURLOPT
    0.51
     ModelExpression
    0.50
     TextAppearance
    0.50
     seeing
    0.50
    seeing
    0.49
     AttributeSet
    0.49
    see
    0.48
     MainAxisSize
    0.47
    Activations Density 0.001%

    No Known Activations