© 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. 93606
    Prev
    Next
    INDEX
    Explanations

    places

    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
    NamedQuery
    -0.54
    rubin
    -0.54
    Obrázky
    -0.53
    PreInfinity
    -0.49
     neur
    -0.48
    Ish
    -0.46
    ghter
    -0.46
     getopt
    -0.46
    Lyric
    -0.45
    gnore
    -0.45
    POSITIVE LOGITS
     kasarigan
    0.81
    __":
    0.72
    __':
    0.68
    MigrationBuilder
    0.66
     Township
    0.65
     <<<<<<<<<<<<<<
    0.61
    __":
    0.61
     TestBed
    0.61
    adpleegd
    0.60
     שוליים
    0.59
    Activations Density 0.005%

    No Known Activations