© 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. 39891
    Prev
    Next
    INDEX
    Explanations

    code snippets

    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
    bians
    -1.08
    SequentialGroup
    -0.63
    enumi
    -0.61
     otu
    -0.55
     paleta
    -0.51
    TemporalType
    -0.50
     floss
    -0.49
    UAGE
    -0.49
    gestone
    -0.48
    inete
    -0.47
    POSITIVE LOGITS
    PRWEB
    0.68
    WriteBarrier
    0.63
    ########.
    0.61
    forChild
    0.61
    RTCF
    0.60
     referenties
    0.58
     egli
    0.57
     protoimpl
    0.57
    AddColumn
    0.56
    VersionUID
    0.54
    Activations Density 0.804%

    No Known Activations