© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 97620
    Prev
    Next
    INDEX
    Explanations

    technical/informational text

    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
    <bos>
    -0.38
     comerciais
    -0.32
     reprodução
    -0.31
     copertura
    -0.31
     finally
    -0.30
     pressione
    -0.30
    nag
    -0.29
    ificação
    -0.29
     épu
    -0.29
     pubblicità
    -0.28
    POSITIVE LOGITS
    GEBURTSDATUM
    1.03
    Tikang
    0.87
     TestBed
    0.86
    Билгалдахарш
    0.82
    OGND
    0.82
    Hochspringen
    0.77
    ReadAll
    0.77
     ostavi
    0.77
    StoryboardSegue
    0.74
    Portale
    0.73
    Activations Density 0.000%

    No Known Activations