© 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
    2. Gemma-2-2B
    3. 5-CLT-HP
    4. 96242
    Prev
    Next
    INDEX
    Explanations

    Asked

    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
     sempat
    -0.52
     during
    -0.47
     when
    -0.47
     auge
    -0.46
     camped
    -0.45
    Incluso
    -0.44
    gezogen
    -0.43
    ✨:
    -0.43
    inely
    -0.42
     нрави
    -0.42
    POSITIVE LOGITS
     tomorrow
    0.73
    ConstraintMaker
    0.72
    RunAsync
    0.71
    ]--;
    0.67
     morrow
    0.66
     amanhã
    0.66
     domani
    0.65
    rungsseite
    0.65
     demain
    0.65
     AppCompatTheme
    0.63
    Activations Density 0.009%

    No Known Activations