© 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. 0-CLT-HP
    7. 91990
    Prev
    Next
    INDEX
    Explanations

    apprentices

    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
    Cal
    -0.72
     purpoſe
    -0.71
     ſte
    -0.65
     uſe
    -0.65
    CAL
    -0.64
     ſche
    -0.64
     TAMBÉM
    -0.63
     foreign
    -0.63
     CAL
    -0.60
     térmico
    -0.59
    POSITIVE LOGITS
    KommentareTeilen
    0.66
     Sto
    0.61
    alamus
    0.59
    crats
    0.55
    PyExc
    0.54
    plained
    0.53
    enced
    0.52
    statics
    0.52
     Pl
    0.52
     F
    0.50
    Activations Density 0.029%

    No Known Activations