© 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. 5-CLT-HP
    7. 2570
    Prev
    Next
    INDEX
    Explanations

    Ancestry

    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
     Winkler
    -0.61
    IZON
    -0.60
    onien
    -0.58
     wirk
    -0.55
    protoimpl
    -0.55
     Krum
    -0.55
    tvguidetime
    -0.54
    Autoritní
    -0.53
    OAK
    -0.52
    POSITIVE LOGITS
     tartalomajánló
    0.49
    didSet
    0.46
    FirstResponder
    0.45
    ImageContext
    0.44
    TableField
    0.44
     nachts
    0.44
    TemporalType
    0.43
    setHorizontal
    0.43
    principalTable
    0.43
     Révolution
    0.43
    Activations Density 0.003%

    No Known Activations