© 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. 38735
    Prev
    Next
    INDEX
    Explanations

    Beginning of articles

    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
     bö
    -0.43
    é
    -0.40
    oneofs
    -0.40
     cip
    -0.38
     mit
    -0.38
    ện
    -0.38
     pe
    -0.37
     DIA
    -0.37
    <bos>
    -0.36
     mel
    -0.36
    POSITIVE LOGITS
    ReusableCell
    0.74
     NUKAT
    0.69
     viewDidLoad
    0.68
    errHandler
    0.67
    indd
    0.65
    UnknownFieldSet
    0.65
     gynhyrchwyd
    0.64
    RepeatedField
    0.64
    InjectAttribute
    0.62
     wireType
    0.61
    Activations Density 0.177%

    No Known Activations