© 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. 1-CLT-HP
    7. 13002
    Prev
    Next
    INDEX
    Explanations

    is

    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
     ktorá
    -0.44
    Mediabestanden
    -0.43
     calore
    -0.42
     která
    -0.39
    -0.39
     kecil
    -0.38
     rapports
    -0.38
    rück
    -0.37
    חד
    -0.37
     beginnetje
    -0.36
    POSITIVE LOGITS
     why
    0.92
     IBOutlet
    0.83
    enderror
    0.82
    awtextra
    0.75
    DockStyle
    0.75
     للاسماء
    0.74
    SourceChecksum
    0.72
     gynhyrchwyd
    0.72
     propOrder
    0.71
    ########.
    0.70
    Activations Density 0.056%

    No Known Activations