© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-CLT-HP
    7. 351
    Prev
    Next
    INDEX
    Explanations

    range

    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
    Besos
    -0.42
     bằng
    -0.41
     PyLong
    -0.40
     pamamagitan
    -0.40
    ModelForm
    -0.40
     Lordships
    -0.39
    ungsbedingungen
    -0.38
     Kombat
    -0.38
    mb
    -0.37
    ştır
    -0.37
    POSITIVE LOGITS
    şiv
    0.76
    oredCriteria
    0.66
     BoxDecoration
    0.63
    ]='\
    0.59
     незавершена
    0.56
    ochrom
    0.55
    cupa
    0.53
    UnitTesting
    0.53
     Italijani
    0.53
    cinogen
    0.53
    Activations Density 0.007%

    No Known Activations