© 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. 1128
    Prev
    Next
    INDEX
    Explanations

    ready

    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
    InjectAttribute
    -0.50
     to
    -0.49
     ligiloj
    -0.48
    RegistryLite
    -0.47
    lence
    -0.47
    Lähteet
    -0.47
    busters
    -0.47
    avelmente
    -0.46
    oare
    -0.45
    出版年
    -0.45
    POSITIVE LOGITS
    bumptech
    0.63
    WSGI
    0.60
    TacToe
    0.57
    .
    0.54
     OMITBAD
    0.54
    NameValuePair
    0.53
    WaitGroup
    0.53
    stdc
    0.52
    viewDidLoad
    0.52
     Alembic
    0.52
    Activations Density 0.035%

    No Known Activations