© 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. 96245
    Prev
    Next
    INDEX
    Explanations

    jam

    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
     ujednoznacz
    -0.69
     AssemblyCulture
    -0.63
    GOTREF
    -0.61
     seemed
    -0.60
     had
    -0.60
     propOrder
    -0.60
     NSCoder
    -0.58
    msgTypes
    -0.58
     consisted
    -0.56
     was
    -0.56
    POSITIVE LOGITS
     kiedyś
    0.56
     allá
    0.56
    PhysRevLett
    0.54
     crescere
    0.52
    ValueGeneration
    0.52
    hability
    0.52
     IOM
    0.52
     SKS
    0.52
    tvguidetime
    0.51
    nhung
    0.51
    Activations Density 0.017%

    No Known Activations