© 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. 5-CLT-HP
    7. 96154
    Prev
    Next
    INDEX
    Explanations

    of

    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
    __':
    -0.65
    __":
    -0.62
    kháu
    -0.58
     PAZ
    -0.57
     MRT
    -0.57
     Administrativna
    -0.56
     chi̍t
    -0.56
    StoreMessageInfo
    -0.54
    setVerticalGroup
    -0.54
    fico
    -0.52
    POSITIVE LOGITS
    origen
    0.64
     HasFactory
    0.61
    ✨:
    0.58
    docks
    0.54
    arache
    0.51
     '\\;'
    0.48
     canali
    0.47
     Containment
    0.46
     stork
    0.45
    onatos
    0.44
    Activations Density 0.002%

    No Known Activations