© 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. 20-CLT-HP
    7. 74653
    Prev
    Next
    INDEX
    Explanations

    European topics

    np_max-act-logits · 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
    IMPORTED
    -0.49
     AppModule
    -0.49
    SwitchCompat
    -0.48
     nahilalakip
    -0.47
    perative
    -0.47
     OMITBAD
    -0.47
    gridx
    -0.47
    InputTagHelper
    -0.46
    WaitGroup
    -0.46
     defaultstate
    -0.45
    POSITIVE LOGITS
     שוליים
    0.63
     Trojans
    0.56
     Cæsar
    0.56
    ########.
    0.56
     Rib
    0.56
     Ruf
    0.54
     RIPRODUZIONE
    0.54
     Rim
    0.52
    iyle
    0.52
     Barb
    0.52
    Activations Density 0.001%

    No Known Activations