© 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. 4476
    Prev
    Next
    INDEX
    Explanations

    soft

    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
    Personendaten
    -0.84
    Autoritní
    -0.82
     estimés
    -0.82
     intptr
    -0.81
     يتيمه
    -0.77
    تقاوى
    -0.77
     propOrder
    -0.76
     AssemblyVersion
    -0.75
     linkovi
    -0.72
    RTDA
    -0.71
    POSITIVE LOGITS
     Kond
    0.44
     Bon
    0.44
     G
    0.44
     means
    0.44
    tte
    0.43
    yste
    0.43
     ge
    0.42
    γον
    0.42
    ulman
    0.41
    gero
    0.41
    Activations Density 0.001%

    No Known Activations