© 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. 20-CLT-HP
    4. 74690
    Prev
    Next
    INDEX
    Explanations

    tumor

    np_max-act-logits · 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
     ||=
    -0.51
     fairness
    -0.51
     Katzen
    -0.50
    copg
    -0.49
     traps
    -0.49
    quine
    -0.49
     Beg
    -0.49
    izare
    -0.49
     Traps
    -0.48
    )|^{
    -0.48
    POSITIVE LOGITS
    protoimpl
    0.53
     free
    0.51
    free
    0.48
    lardır
    0.47
    GraphicsUnit
    0.46
    SharedDtor
    0.44
    illite
    0.44
     IndexPath
    0.43
     opérés
    0.43
     FileInputStream
    0.43
    Activations Density 0.003%

    No Known Activations