© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 94835
    Prev
    Next
    INDEX
    Explanations

    flow

    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
     flow
    -2.48
    flow
    -2.17
     flowed
    -2.08
     Flow
    -2.06
    Flow
    -1.97
     flows
    -1.95
     flowing
    -1.91
     FLOW
    -1.82
    flows
    -1.73
    flowing
    -1.67
    POSITIVE LOGITS
    parsedMessage
    0.68
    FieldBuilder
    0.66
    
    0.65
    ⓧ
    0.63
    UnknownFields
    0.59
    \{\\
    0.57
    ophores
    0.57
    ksikon
    0.56
    initions
    0.55
    DebuggerNonUser
    0.54
    Activations Density 0.362%

    No Known Activations