© 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. 4-CLT-HP
    7. 4426
    Prev
    Next
    INDEX
    Explanations

    time

    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
    phal
    -0.59
     ومل
    -0.59
     présidentielle
    -0.59
    ImageField
    -0.55
    !("{
    -0.55
    ³/
    -0.54
     betweenstory
    -0.54
    platin
    -0.53
    berichte
    -0.53
    orescence
    -0.53
    POSITIVE LOGITS
     to
    0.59
    GEBURTSDATUM
    0.53
    rrggbb
    0.51
    TypedDataSet
    0.45
     estekak
    0.43
     Reverso
    0.41
    FetchType
    0.40
     utafitiHapana
    0.40
     RW
    0.40
    seteq
    0.40
    Activations Density 0.001%

    No Known Activations