© 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. 0-CLT-HP
    4. 91972
    Prev
    Next
    INDEX
    Explanations

    iller

    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
    fted
    -0.55
    ing
    -0.53
    zak
    -0.49
    cting
    -0.48
    tvguidetime
    -0.47
    middle
    -0.47
    ásban
    -0.46
    ssysteme
    -0.45
    cted
    -0.45
    ner
    -0.44
    POSITIVE LOGITS
     oprot
    0.75
    Personensuche
    0.75
    MockBean
    0.72
     '\\;'
    0.71
    OrBuilder
    0.70
    LookAnd
    0.70
    urlpatterns
    0.64
    CPtr
    0.63
    rungsseite
    0.63
     تانيه
    0.63
    Activations Density 0.262%

    No Known Activations