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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 45500
    Prev
    Next
    INDEX
    Explanations

    strategies and policies

    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
     invokingState
    -0.74
    JvmStatic
    -0.61
    Strategy
    -0.59
     Supervisory
    -0.59
    ally
    -0.56
    stylers
    -0.56
    rook
    -0.54
    DebuggerNonUser
    -0.54
     modes
    -0.52
    parity
    -0.52
    POSITIVE LOGITS
    roek
    0.59
     colorés
    0.58
    VersionUID
    0.57
    Tracce
    0.57
     mérit
    0.54
     meurt
    0.54
     semmi
    0.54
     mourut
    0.53
     juzg
    0.53
     fotográfico
    0.53
    Activations Density 1.205%

    No Known Activations