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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 709
    Prev
    Next
    INDEX
    Explanations

    Difficulty, effort

    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
    rungsseite
    -0.76
    Życiorys
    -0.75
     Normdatei
    -0.71
    migrationBuilder
    -0.68
     disambiguazione
    -0.64
    MENAFN
    -0.60
    })]
    -0.59
    Demografie
    -0.58
    posedge
    -0.57
    WebElementEntity
    -0.56
    POSITIVE LOGITS
     inmediato
    0.49
    bueno
    0.48
     fixing
    0.44
     nourrir
    0.43
    She
    0.43
    __);
    0.42
    selling
    0.42
     attravers
    0.42
     المهم
    0.41
     Audiodateien
    0.41
    Activations Density 0.004%

    No Known Activations